Full Code of fangleai/TransformerCVAE for AI

Repository: fangleai/TransformerCVAE
Branch: master
Commit: 6d314bcd5bd6
Files: 26
Total size: 38.5 MB

Directory structure:
gitextract_x8c_d3k7/

├── README.md
├── data/
│   ├── __init__.py
│   ├── arxiv/
│   │   ├── artificial intelligence_10047_15000_15_abs.txt
│   │   ├── artificial intelligence_10047_15000_15_title.txt
│   │   ├── artificial intelligence_134_15000_200_abs.txt
│   │   ├── artificial intelligence_134_15000_200_title.txt
│   │   ├── computer vision_14582_15000_15_abs.txt
│   │   ├── computer vision_14582_15000_15_title.txt
│   │   ├── language generation_14514_15000_15_abs.txt
│   │   └── language generation_14514_15000_15_title.txt
│   ├── arxiv_dataset.py
│   ├── plot_dataset.py
│   ├── prompt_dataset.py
│   ├── util.py
│   └── yelp_dataset.py
├── dist_utils.py
├── eval_ppl.py
├── eval_ppl_prefix.py
├── generate.py
├── generate_prefix.py
├── model.py
├── train.py
├── train_dist.py
├── train_dist_half.py
├── tsne_plot.py
└── util.py

================================================
FILE CONTENTS
================================================

================================================
FILE: README.md
================================================
# TransformerCVAE

This repository contains source code for paper [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://arxiv.org/abs/2101.00828):

```
@article{fang2021transformer,
  title={Transformer-based Conditional Variational Autoencoder for Controllable Story Generation},
  author={Fang, Le and Zeng, Tao and Liu, Chaochun and Bo, Liefeng and Dong, Wen and Chen, Changyou},
  journal={arXiv preprint arXiv:2101.00828},
  year={2021}
}
```

0. get source data ([Arxiv](https://github.com/gcunhase/ArXivAbsTitleDataset), [Yelp](https://github.com/fangleai/Implicit-LVM/tree/master/lang_model_yelp/data), [WritingPrompts](https://github.com/pytorch/fairseq/blob/master/examples/stories/README.md), [WikiPlots](https://github.com/markriedl/WikiPlots)).
1. data pre-processing (data/).
2. training (choose from several different implementations on parallelism and precision: train.py, train_dist.py, train_dist_half.py).
3. generation, evaluation and analysis (generate.py/generate_prefix.py, eval_ppl.py/eval_ppl_prefix.py, tsne_plot.py).

Contact: lefang@buffalo.edu

Update on 2022:
If you encounter package version issue, sorry for that I don't have a requirements.txt with exact versions. I used this package: https://github.com/nvidia/apex and an old pytorch version compatible with it at that time, say pytorch=0.4 (not 100% sure).


================================================
FILE: data/__init__.py
================================================


================================================
FILE: data/arxiv/artificial intelligence_10047_15000_15_abs.txt
================================================
Artificial intelligence has impacted many aspects of human life. This paper studies the impact of artificial intelligence on economic theory. In particular we study the impact of artificial intelligence on the theory of bounded rationality, efficient market hypothesis and prospect theory.
In this paper, I put forward that in many instances, thinking mechanisms are equivalent to artificial intelligence modules programmed into the human mind.
The rapid development of artificial intelligence has brought the artificial intelligence threat theory as well as the problem about how to evaluate the intelligence level of intelligent products. Both need to find a quantitative method to evaluate the intelligence level of intelligence systems, including human intelligence. Based on the standard intelligence system and the extended Von Neumann architecture, this paper proposes General IQ, Service IQ and Value IQ evaluation methods for intelligence systems, depending on different evaluation purposes. Among them, the General IQ of intelligence systems is to answer the question of whether the artificial intelligence can surpass the human intelligence, which is reflected in putting the intelligence systems on an equal status and conducting the unified evaluation. The Service IQ and Value IQ of intelligence systems are used to answer the question of how the intelligent products can better serve the human, reflecting the intelligence and required cost of each intelligence system as a product in the process of serving human.
In this article, I discuss how the AI community views concerns about the emergence of superintelligent AI and related philosophical issues.
Currently, potential threats of artificial intelligence (AI) to human have triggered a large controversy in society, behind which, the nature of the issue is whether the artificial intelligence (AI) system can be evaluated quantitatively. This article analyzes and evaluates the challenges that the AI development level is facing, and proposes that the evaluation methods for the human intelligence test and the AI system are not uniform; and the key reason for which is that none of the models can uniformly describe the AI system and the beings like human. Aiming at this problem, a standard intelligent system model is established in this study to describe the AI system and the beings like human uniformly. Based on the model, the article makes an abstract mathematical description, and builds the standard intelligent machine mathematical model; expands the Von Neumann architecture and proposes the Liufeng - Shiyong architecture; gives the definition of the artificial intelligence IQ, and establishes the artificial intelligence scale and the evaluation method; conduct the test on 50 search engines and three human subjects at different ages across the world, and finally obtains the ranking of the absolute IQ and deviation IQ ranking for artificial intelligence IQ 2014.
Knowledge-based or Artificial Intelligence techniques are used increasingly as alternatives to more classical techniques to model ENVIRONMENTAL SYSTEMS. Use of Artificial Intelligence (AI) in environmental modelling has increased with recognition of its potential. In this paper we examine the DIFFERENT TECHNIQUES of Artificial intelligence with profound examples of human perception, learning and reasoning to solve complex problems. However with the increase of complexity better methods are required. Keeping in view of the above some researchers introduced the idea of hybrid mechanism in which two or more methods can be combined which seems to be a positive effort for creating a more complex; advanced and intelligent system which has the capability to in- cooperate human decisions thus driving the landscape changes.
Although the definition and measurement of intelligence is clearly of fundamental importance to the field of artificial intelligence, no general survey of definitions and tests of machine intelligence exists. Indeed few researchers are even aware of alternatives to the Turing test and its many derivatives. In this paper we fill this gap by providing a short survey of the many tests of machine intelligence that have been proposed.
The Universal Intelligence Measure is a recently proposed formal definition of intelligence. It is mathematically specified, extremely general, and captures the essence of many informal definitions of intelligence. It is based on Hutter's Universal Artificial Intelligence theory, an extension of Ray Solomonoff's pioneering work on universal induction. Since the Universal Intelligence Measure is only asymptotically computable, building a practical intelligence test from it is not straightforward. This paper studies the practical issues involved in developing a real-world UIM-based performance metric. Based on our investigation, we develop a prototype implementation which we use to evaluate a number of different artificial agents.
We derive axiomatically the probability function that should be used to make decisions given any form of underlying uncertainty.
This article analyses the properties of the Internal Behaviour network, an action selection mechanism previously proposed by the authors, with the aid of a simulation developed for such ends. A brief review of the Internal Behaviour network is followed by the explanation of the implementation of the simulation. Then, experiments are presented and discussed analysing the properties of the action selection in the proposed model.
This paper describe about a new methodology for developing and improving the robotics field via artificial intelligence and internet of things. Now a day, we can say Artificial Intelligence take the world into robotics. Almost all industries use robots for lot of works. They are use co-operative robots to make different kind of works. But there was some problem to make robot for multi tasks. So there was a necessary new methodology to made multi tasking robots. It will be done only by artificial intelligence and internet of things.
Over the last decade, there has been growing interest in the use or measures or change in belief for reasoning with uncertainty in artificial intelligence research. An important characteristic of several methodologies that reason with changes in belief or belief updates, is a property that we term modularity. We call updates that satisfy this property modular updates. Whereas probabilistic measures of belief update - which satisfy the modularity property were first discovered in the nineteenth century, knowledge and discussion of these quantities remains obscure in artificial intelligence research. We define modular updates and discuss their inappropriate use in two influential expert systems.
One of the most important aims of the fields of robotics, artificial intelligence and artificial life is the design and construction of systems and machines as versatile and as reliable as living organisms at performing high level human-like tasks. But how are we to evaluate artificial systems if we are not certain how to measure these capacities in living systems, let alone how to define life or intelligence? Here I survey a concrete metric towards measuring abstract properties of natural and artificial systems, such as the ability to react to the environment and to control one's own behaviour.
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this measure formally captures the concept of machine intelligence in the broadest reasonable sense.
Narrative intelligence is the ability to craft, tell, understand, and respond affectively to stories. We argue that instilling artificial intelligences with computational narrative intelligence affords a number of applications beneficial to humans. We lay out some of the machine learning challenges necessary to solve to achieve computational narrative intelligence. Finally, we argue that computational narrative is a practical step towards machine enculturation, the teaching of sociocultural values to machines.
The advent of artificial intelligence has changed many disciplines such as engineering, social science and economics. Artificial intelligence is a computational technique which is inspired by natural intelligence such as the swarming of birds, the working of the brain and the pathfinding of the ants. These techniques have impact on economic theories. This book studies the impact of artificial intelligence on economic theories, a subject that has not been extensively studied. The theories that are considered are: demand and supply, asymmetrical information, pricing, rational choice, rational expectation, game theory, efficient market hypotheses, mechanism design, prospect, bounded rationality, portfolio theory, rational counterfactual and causality. The benefit of this book is that it evaluates existing theories of economics and update them based on the developments in artificial intelligence field.
In this paper we offer a formal definition of Artificial Intelligence and this directly gives us an algorithm for construction of this object. Really, this algorithm is useless due to the combinatory explosion.   The main innovation in our definition is that it does not include the knowledge as a part of the intelligence. So according to our definition a newly born baby also is an Intellect. Here we differs with Turing's definition which suggests that an Intellect is a person with knowledge gained through the years.
With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community. Building on our previous work on AI Containment Problem we propose a number of guidelines which should help AI safety researchers to develop reliable sandboxing software for intelligent programs of all levels. Such safety container software will make it possible to study and analyze intelligent artificial agent while maintaining certain level of safety against information leakage, social engineering attacks and cyberattacks from within the container.
Content marketing is todays one of the most remarkable approaches in the context of marketing processes of companies. Value of this kind of marketing has improved in time, thanks to the latest developments regarding to computer and communication technologies. Nowadays, especially social media based platforms have a great importance on enabling companies to design multimedia oriented, interactive content. But on the other hand, there is still something more to do for improved content marketing approaches. In this context, objective of this study is to focus on intelligent content marketing, which can be done by using artificial intelligence. Artificial Intelligence is todays one of the most remarkable research fields and it can be used easily as multidisciplinary. So, this study has aimed to discuss about its potential on improving content marketing. In detail, the study has enabled readers to improve their awareness about the intersection point of content marketing and artificial intelligence. Furthermore, the authors have introduced some example models of intelligent content marketing, which can be achieved by using current Web technologies and artificial intelligence techniques.
The recent surge in interest in ethics in artificial intelligence may leave many educators wondering how to address moral, ethical, and philosophical issues in their AI courses. As instructors we want to develop curriculum that not only prepares students to be artificial intelligence practitioners, but also to understand the moral, ethical, and philosophical impacts that artificial intelligence will have on society. In this article we provide practical case studies and links to resources for use by AI educators. We also provide concrete suggestions on how to integrate AI ethics into a general artificial intelligence course and how to teach a stand-alone artificial intelligence ethics course.
There is a significant lack of unified approaches to building generally intelligent machines. The majority of current artificial intelligence research operates within a very narrow field of focus, frequently without considering the importance of the 'big picture'. In this document, we seek to describe and unify principles that guide the basis of our development of general artificial intelligence. These principles revolve around the idea that intelligence is a tool for searching for general solutions to problems. We define intelligence as the ability to acquire skills that narrow this search, diversify it and help steer it to more promising areas. We also provide suggestions for studying, measuring, and testing the various skills and abilities that a human-level intelligent machine needs to acquire. The document aims to be both implementation agnostic, and to provide an analytic, systematic, and scalable way to generate hypotheses that we believe are needed to meet the necessary conditions in the search for general artificial intelligence. We believe that such a framework is an important stepping stone for bringing together definitions, highlighting open problems, connecting researchers willing to collaborate, and for unifying the arguably most significant search of this century.
Artificial intelligence (AI) is an important technology that supports daily social life and economic activities. It contributes greatly to the sustainable growth of Japan's economy and solves various social problems. In recent years, AI has attracted attention as a key for growth in developed countries such as Europe and the United States and developing countries such as China and India. The attention has been focused mainly on developing new artificial intelligence information communication technology (ICT) and robot technology (RT). Although recently developed AI technology certainly excels in extracting certain patterns, there are many limitations. Most ICT models are overly dependent on big data, lack a self-idea function, and are complicated. In this paper, rather than merely developing next-generation artificial intelligence technology, we aim to develop a new concept of general-purpose intelligence cognition technology called Beyond AI. Specifically, we plan to develop an intelligent learning model called Brain Intelligence (BI) that generates new ideas about events without having experienced them by using artificial life with an imagine function. We will also conduct demonstrations of the developed BI intelligence learning model on automatic driving, precision medical care, and industrial robots.
Although artificial intelligence is currently one of the most interesting areas in scientific research, the potential threats posed by emerging AI systems remain a source of persistent controversy. To address the issue of AI threat, this study proposes a standard intelligence model that unifies AI and human characteristics in terms of four aspects of knowledge, i.e., input, output, mastery, and creation. Using this model, we observe three challenges, namely, expanding of the von Neumann architecture; testing and ranking the intelligence quotient of naturally and artificially intelligent systems, including humans, Google, Bing, Baidu, and Siri; and finally, the dividing of artificially intelligent systems into seven grades from robots to Google Brain. Based on this, we conclude that AlphaGo belongs to the third grade.
Biologically inspired computing is an area of computer science which uses the advantageous properties of biological systems. It is the amalgamation of computational intelligence and collective intelligence. Biologically inspired mechanisms have already proved successful in achieving major advances in a wide range of problems in computing and communication systems. The consortium of bio-inspired computing are artificial neural networks, evolutionary algorithms, swarm intelligence, artificial immune systems, fractal geometry, DNA computing and quantum computing, etc. This article gives an introduction to swarm intelligence.
This paper analyses the influence of including agents of different degrees of intelligence in a multiagent system. The goal is to better understand how we can develop intelligence tests that can evaluate social intelligence. We analyse several reinforcement algorithms in several contexts of cooperation and competition. Our experimental setting is inspired by the recently developed Darwin-Wallace distribution.
We give a brief overview of the main characteristics of diagrammatic reasoning, analyze a case of human reasoning in a mastermind game, and explain why hybrid representation systems (HRS) are particularly attractive and promising for Artificial General Intelligence and Computer Science in general.
We reminisce and discuss applications of algorithmic probability to a wide range of problems in artificial intelligence, philosophy and technological society. We propose that Solomonoff has effectively axiomatized the field of artificial intelligence, therefore establishing it as a rigorous scientific discipline. We also relate to our own work in incremental machine learning and philosophy of complexity.
Much artificial intelligence research focuses on the problem of deducing the validity of unobservable propositions or hypotheses from observable evidence.! Many of the knowledge representation techniques designed for this problem encode the relationship between evidence and hypothesis in a directed manner. Moreover, the direction in which evidence is stored is typically from evidence to hypothesis.
This paper covers two topics: first an introduction to Algorithmic Complexity Theory: how it defines probability, some of its characteristic properties and past successful applications. Second, we apply it to problems in A.I. - where it promises to give near optimum search procedures for two very broad classes of problems.
Verified artificial intelligence (AI) is the goal of designing AI-based systems that are provably correct with respect to mathematically-specified requirements. This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.
Human speech is the most important part of General Artificial Intelligence and subject of much research. The hypothesis proposed in this article provides explanation of difficulties that modern science tackles in the field of human brain simulation. The hypothesis is based on the author's conviction that the brain of any given person has different ability to process and store information. Therefore, the approaches that are currently used to create General Artificial Intelligence have to be altered.
This article considers evidence from physical and biological sciences to show machines are deficient compared to biological systems at incorporating intelligence. Machines fall short on two counts: firstly, unlike brains, machines do not self-organize in a recursive manner; secondly, machines are based on classical logic, whereas Nature's intelligence may depend on quantum mechanics.
Artificial Intelligence began as a field probing some of the most fundamental questions of science - the nature of intelligence and the design of intelligent artifacts. But it has grown into a discipline that is deeply entwined with commerce and society. Today's AI technology, such as expert systems and intelligent assistants, pose some difficult questions of risk, trust and accountability. In this paper, we present these concerns, examining them in the context of historical developments that have shaped the nature and direction of AI research. We also suggest the exploration and further development of two paradigms, human intelligence-machine cooperation, and a sociological view of intelligence, which might help address some of these concerns.
Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building. Intelligent machines will help everywhere. However, this bright future has a dark side: a dramatic job market contraction before its unpredictable transformation. Hence, in a near future, large numbers of job seekers will need financial support while catching up with these novel unpredictable jobs. This possible job market crisis has an antidote inside. In fact, the rise of AI is sustained by the biggest knowledge theft of the recent years. Learning AI machines are extracting knowledge from unaware skilled or unskilled workers by analyzing their interactions. By passionately doing their jobs, these workers are digging their own graves.   In this paper, we propose Human-in-the-loop Artificial Intelligence (HIT-AI) as a fairer paradigm for Artificial Intelligence systems. HIT-AI will reward aware and unaware knowledge producers with a different scheme: decisions of AI systems generating revenues will repay the legitimate owners of the knowledge used for taking those decisions. As modern Robin Hoods, HIT-AI researchers should fight for a fairer Artificial Intelligence that gives back what it steals.
Independent from the still ongoing research in measuring individual intelligence, we anticipate and provide a framework for measuring collective intelligence. Collective intelligence refers to the idea that several individuals can collaborate in order to achieve high levels of intelligence. We present thus some ideas on how the intelligence of a group can be measured and simulate such tests. We will however focus here on groups of artificial intelligence agents (i.e., machines). We will explore how a group of agents is able to choose the appropriate problem and to specialize for a variety of tasks. This is a feature which is an important contributor to the increase of intelligence in a group (apart from the addition of more agents and the improvement due to common decision making). Our results reveal some interesting results about how (collective) intelligence can be modeled, about how collective intelligence tests can be designed and about the underlying dynamics of collective intelligence. As it will be useful for our simulations, we provide also some improvements of the threshold allocation model originally used in the area of swarm intelligence but further generalized here.
Crisis response poses many of the most difficult information technology in crisis management. It requires information and communication-intensive efforts, utilized for reducing uncertainty, calculating and comparing costs and benefits, and managing resources in a fashion beyond those regularly available to handle routine problems. In this paper, we explore the benefits of artificial intelligence technologies in crisis response. This paper discusses the role of artificial intelligence technologies; namely, robotics, ontology and semantic web, and multi-agent systems in crisis response.
Agents and agent systems are becoming more and more important in the development of a variety of fields such as ubiquitous computing, ambient intelligence, autonomous computing, intelligent systems and intelligent robotics. The need for improvement of our basic knowledge on agents is very essential. We take a systematic approach and present extended classification of artificial agents which can be useful for understanding of what artificial agents are and what they can be in the future. The aim of this classification is to give us insights in what kind of agents can be created and what type of problems demand a specific kind of agents for their solution.
Two different definitions of the Artificial Intelligence concept have been proposed in papers [1] and [2]. The first definition is informal. It says that any program that is cleverer than a human being, is acknowledged as Artificial Intelligence. The second definition is formal because it avoids reference to the concept of human being. The readers of papers [1] and [2] might be left with the impression that both definitions are equivalent and the definition in [2] is simply a formal version of that in [1]. This paper will compare both definitions of Artificial Intelligence and, hopefully, will bring a better understanding of the concept.
Computer games play an important role in our society and motivate people to learn computer science. Since artificial intelligence is integral to most games, they can also be used to teach artificial intelligence. We introduce the Game AI Game Engine (GAIGE), a Python game engine specifically designed to teach about how AI is used in computer games. A progression of seven assignments builds toward a complete, working Multi-User Battle Arena (MOBA) game. We describe the engine, the assignments, and our experiences using it in a class on Game Artificial Intelligence.
This paper is concerned with two theories of probability judgment: the Bayesian theory and the theory of belief functions. It illustrates these theories with some simple examples and discusses some of the issues that arise when we try to implement them in expert systems. The Bayesian theory is well known; its main ideas go back to the work of Thomas Bayes (1702-1761). The theory of belief functions, often called the Dempster-Shafer theory in the artificial intelligence community, is less well known, but it has even older antecedents; belief-function arguments appear in the work of George Hooper (16401723) and James Bernoulli (1654-1705). For elementary expositions of the theory of belief functions, see Shafer (1976, 1985).
Algorithmic composition is the partial or total automation of the process of music composition by using computers. Since the 1950s, different computational techniques related to Artificial Intelligence have been used for algorithmic composition, including grammatical representations, probabilistic methods, neural networks, symbolic rule-based systems, constraint programming and evolutionary algorithms. This survey aims to be a comprehensive account of research on algorithmic composition, presenting a thorough view of the field for researchers in Artificial Intelligence.
The theory of rational choice assumes that when people make decisions they do so in order to maximize their utility. In order to achieve this goal they ought to use all the information available and consider all the choices available to choose an optimal choice. This paper investigates what happens when decisions are made by artificially intelligent machines in the market rather than human beings. Firstly, the expectations of the future are more consistent if they are made by an artificially intelligent machine and the decisions are more rational and thus marketplace becomes more rational.
Artificial Intelligence (AI) started out with an ambition to reproduce the human mind, but, as the sheer scale of that ambition became apparent, quickly retreated into either studying specialized intelligent behaviours, or proposing overarching architectural concepts for interfacing specialized intelligent behaviour components, conceived of as agents in a kind of organization. This agent-based modeling paradigm, in turn, proves to have interesting applications in understanding, simulating, and predicting the behaviour of social and legal structures on an aggregate level. This chapter examines a number of relevant cross-cutting concerns, conceptualizations, modeling problems and design challenges in large-scale distributed Artificial Intelligence, as well as in institutional systems, and identifies potential grounds for novel advances.
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. In order to trust their behavior, we must make it intelligible --- either by using inherently interpretable models or by developing methods for explaining otherwise overwhelmingly complex decisions by local approximation, vocabulary alignment, and interactive dialog.
How intelligent is robot A compared with robot B? And how intelligent are robots A and B compared with animals (or plants) X and Y? These are both interesting and deeply challenging questions. In this paper we address the question "how intelligent is your intelligent robot?" by proposing that embodied intelligence emerges from the interaction and integration of four different and distinct kinds of intelligence. We then suggest a simple diagrammatic representation on which these kinds of intelligence are shown as four axes in a star diagram. A crude qualitative comparison of the intelligence graphs of animals and robots both exposes and helps to explain the chronic intelligence deficit of intelligent robots. Finally we examine the options for determining numerical values for the four kinds of intelligence in an effort to move toward a quantifiable intelligence vector.
On grounds of the discussed material, we reason about possible future development of quantum game theory and its impact on information processing and the emerging information society. The idea of quantum artificial intelligence is explained.
We show that the d -separation criterion constitutes a valid test for conditional independence relationships that are induced by feedback systems involving discrete variables.
An elaboration of Dempster's method of constructing belief functions suggests a broadly applicable strategy for constructing lower probabilities under a variety of evidentiary constraints.
This paper examines the concept of a combination rule for belief functions. It is shown that two fairly simple and apparently reasonable assumptions determine Dempster's rule, giving a new justification for it.
Within the transferable belief model, positive basic belief masses can be allocated to the empty set, leading to unnormalized belief functions. The nature of these unnormalized beliefs is analyzed.
Definitions and notations with historical references are given for some numerical coefficients commonly used to quantify relations among collections of objects for the purpose of expressing approximate knowledge and probabilistic reasoning.
Smart optical networks are the next evolution of programmable networking and programmable automation of optical networks, with human-in-the-loop network control and management. The paper discusses this evolution and the role of Artificial Intelligence (AI).
The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI researchers avoid discussing intelligence, the award-winning PhD thesis (Legg, 2008) provided the philosophical embedding and investigated the UAI-based universal measure of rational intelligence, which is formal, objective and non-anthropocentric. Recently, effective approximations of AIXI have been derived and experimentally investigated in JAIR paper (Veness et al. 2011). This practical breakthrough has resulted in some impressive applications, finally muting earlier critique that UAI is only a theory. For the first time, without providing any domain knowledge, the same agent is able to self-adapt to a diverse range of interactive environments. For instance, AIXI is able to learn from scratch to play TicTacToe, Pacman, Kuhn Poker, and other games by trial and error, without even providing the rules of the games.   These achievements give new hope that the grand goal of Artificial General Intelligence is not elusive.   This article provides an informal overview of UAI in context. It attempts to gently introduce a very theoretical, formal, and mathematical subject, and discusses philosophical and technical ingredients, traits of intelligence, some social questions, and the past and future of UAI.
Order exists in the world. The intelligence process enables us to realize that order, to some extent. We provide a high level description of intelligence using simple definitions, basic building blocks, a conceptual framework and general hierarchy. This perspective includes multiple levels of abstraction occurring in space and in time. The resulting model offers simple, useful ways to help realize the essence of intelligence.
When human agents come together to make decisions, it is often the case that one human agent has more information than the other. This phenomenon is called information asymmetry and this distorts the market. Often if one human agent intends to manipulate a decision in its favor the human agent can signal wrong or right information. Alternatively, one human agent can screen for information to reduce the impact of asymmetric information on decisions. With the advent of artificial intelligence, signaling and screening have been made easier. This paper studies the impact of artificial intelligence on the theory of asymmetric information. It is surmised that artificial intelligent agents reduce the degree of information asymmetry and thus the market where these agents are deployed become more efficient. It is also postulated that the more artificial intelligent agents there are deployed in the market the less is the volume of trades in the market. This is because for many trades to happen the asymmetry of information on goods and services to be traded should exist, creating a sense of arbitrage.
There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to provide more transparency to their algorithms. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that, if these techniques are to succeed, the explanations they generate should have a structure that humans accept. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a `good' explanation. There exists vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations. This paper argues that the field of explainable artificial intelligence should build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence.
We briefly introduce the memory based approaches to emulate machine intelligence in VLSI hardware, describing the challenges and advantages. Implementation of artificial intelligence techniques in VLSI hardware is a practical and difficult problem. Deep architectures, hierarchical temporal memories and memory networks are some of the contemporary approaches in this area of research. The techniques attempt to emulate low level intelligence tasks and aim at providing scalable solutions to high level intelligence problems such as sparse coding and contextual processing.
Whether the machine intelligence can surpass the human intelligence is a controversial issue. On the basis of traditional IQ, this article presents the Universal IQ test method suitable for both the machine intelligence and the human intelligence. With the method, machine and human intelligences were divided into 4 major categories and 15 subcategories. A total of 50 search engines across the world and 150 persons at different ages were subject to the relevant test. And then, the Universal IQ ranking list of 2014 for the test objects was obtained.
Looks at state interactions from an agent based AI perspective to see state interactions as an example of emergent intelligent behavior. Exposes basic principles of game theory.
This brief note highlights some basic concepts required toward understanding the evolution of machine learning and deep learning models. The note starts with an overview of artificial intelligence and its relationship to biological neuron that ultimately led to the evolution of todays intelligent models.
A introduction to the syntax and Semantics of Answer Set Programming intended as an handout to [under]graduate students taking Artificial Intlligence or Logic Programming classes.
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.
Artificial general intelligence (AGI) refers to research aimed at tackling the full problem of artificial intelligence, that is, create truly intelligent agents. This sets it apart from most AI research which aims at solving relatively narrow domains, such as character recognition, motion planning, or increasing player satisfaction in games. But how do we know when an agent is truly intelligent? A common point of reference in the AGI community is Legg and Hutter's formal definition of universal intelligence, which has the appeal of simplicity and generality but is unfortunately incomputable. Games of various kinds are commonly used as benchmarks for "narrow" AI research, as they are considered to have many important properties. We argue that many of these properties carry over to the testing of general intelligence as well. We then sketch how such testing could practically be carried out. The central part of this sketch is an extension of universal intelligence to deal with finite time, and the use of sampling of the space of games expressed in a suitably biased game description language.
We propose a number of heuristics that can be used for identifying when intransitive choice behaviour is likely to occur in choice situations. We also suggest two methods for avoiding undesired choice behaviour, namely transparent communication and adaptive choice-set generation. We believe that these two ways can contribute to the avoidance of decision biases in choice situations that may often be regretted.
The Hard Problem of consciousness has been dismissed as an illusion. By showing that computers are capable of experiencing, we show that they are at least rudimentarily conscious with potential to eventually reach superconsciousness. The main contribution of the paper is a test for confirming certain subjective experiences in a tested agent. We follow with analysis of benefits and problems with conscious machines and implications of such capability on future of computing, machine rights and artificial intelligence safety.
Our desire and fascination with intelligent machines dates back to the antiquity's mythical automaton Talos, Aristotle's mode of mechanical thought (syllogism) and Heron of Alexandria's mechanical machines and automata. However, the quest for Artificial General Intelligence (AGI) is troubled with repeated failures of strategies and approaches throughout the history. This decade has seen a shift in interest towards bio-inspired software and hardware, with the assumption that such mimicry entails intelligence. Though these steps are fruitful in certain directions and have advanced automation, their singular design focus renders them highly inefficient in achieving AGI. Which set of requirements have to be met in the design of AGI? What are the limits in the design of the artificial? Here, a careful examination of computation in biological systems hints that evolutionary tinkering of contextual processing of information enabled by a hierarchical architecture is the key to build AGI.
The development of artificial general intelligence is considered by many to be inevitable. What such intelligence does after becoming aware is not so certain. To that end, research suggests that the likelihood of artificial general intelligence becoming hostile to humans is significant enough to warrant inquiry into methods to limit such potential. Thus, containment of artificial general intelligence is a timely and meaningful research topic. While there is limited research exploring possible containment strategies, such work is bounded by the underlying field the strategies draw upon. Accordingly, we set out to construct an ontology to describe necessary elements in any future containment technology. Using existing academic literature, we developed a single domain ontology containing five levels, 32 codes, and 32 associated descriptors. Further, we constructed ontology diagrams to demonstrate intended relationships. We then identified humans, AGI, and the cyber world as novel agent objects necessary for future containment activities. Collectively, the work addresses three critical gaps: (a) identifying and arranging fundamental constructs; (b) situating AGI containment within cyber science; and (c) developing scientific rigor within the field.
Artificial intelligence offers superior techniques and methods by which problems from diverse domains may find an optimal solution. The Machine Learning technologies refer to the domain of artificial intelligence aiming to develop the techniques allowing the computers to "learn". Some systems based on Machine Learning technologies tend to eliminate the necessity of the human intelligence while the others adopt a man-machine collaborative approach.
This article is a brief personal account of the past, present, and future of algorithmic randomness, emphasizing its role in inductive inference and artificial intelligence. It is written for a general audience interested in science and philosophy. Intuitively, randomness is a lack of order or predictability. If randomness is the opposite of determinism, then algorithmic randomness is the opposite of computability. Besides many other things, these concepts have been used to quantify Ockham's razor, solve the induction problem, and define intelligence.
There are few knowledge representation (KR) techniques available for efficiently representing knowledge. However, with the increase in complexity, better methods are needed. Some researchers came up with hybrid mechanisms by combining two or more methods. In an effort to construct an intelligent computer system, a primary consideration is to represent large amounts of knowledge in a way that allows effective use and efficiently organizing information to facilitate making the recommended inferences. There are merits and demerits of combinations, and standardized method of KR is needed. In this paper, various hybrid schemes of KR were explored at length and details presented.
This work summarizes part of current knowledge on High-level Cognitive process and its relation with biological hardware. Thus, it is possible to identify some paradoxes which could impact the development of future technologies and artificial intelligence: we may make a High-level Cognitive Machine, sacrificing the principal attribute of a machine, its accuracy.
In this work we investigate the systems that implements algorithms for the planning problem in Artificial Intelligence, called planners, with especial attention to the planners based on the plan graph. We analyze the problem of comparing the performance of the different algorithms and we propose an environment for the development and analysis of planners.
This paper covers a number of approaches that leverage Artificial Intelligence algorithms and techniques to aid Unmanned Combat Aerial Vehicle (UCAV) autonomy. An analysis of current approaches to autonomous control is provided followed by an exploration of how these techniques can be extended and enriched with AI techniques including Artificial Neural Networks (ANN), Ensembling and Reinforcement Learning (RL) to evolve control strategies for UCAVs.
As intelligent systems are increasingly making decisions that directly affect society, perhaps the most important upcoming research direction in AI is to rethink the ethical implications of their actions. Means are needed to integrate moral, societal and legal values with technological developments in AI, both during the design process as well as part of the deliberation algorithms employed by these systems. In this paper, we describe leading ethics theories and propose alternative ways to ensure ethical behavior by artificial systems. Given that ethics are dependent on the socio-cultural context and are often only implicit in deliberation processes, methodologies are needed to elicit the values held by designers and stakeholders, and to make these explicit leading to better understanding and trust on artificial autonomous systems.
AI technology has a long history which is actively and constantly changing and growing. It focuses on intelligent agents, which contain devices that perceive the environment and based on which takes actions in order to maximize goal success chances. In this paper, we will explain the modern AI basics and various representative applications of AI. In the context of the modern digitalized world, AI is the property of machines, computer programs, and systems to perform the intellectual and creative functions of a person, independently find ways to solve problems, be able to draw conclusions and make decisions. Most artificial intelligence systems have the ability to learn, which allows people to improve their performance over time. The recent research on AI tools, including machine learning, deep learning and predictive analysis intended toward increasing the planning, learning, reasoning, thinking and action taking ability. Based on which, the proposed research intends towards exploring on how the human intelligence differs from the artificial intelligence. Moreover, we critically analyze what AI of today is capable of doing, why it still cannot reach human intelligence and what are the open challenges existing in front of AI to reach and outperform human level of intelligence. Furthermore, it will explore the future predictions for artificial intelligence and based on which potential solution will be recommended to solve it within next decades.
Specialized intelligent systems can be found everywhere: finger print, handwriting, speech, and face recognition, spam filtering, chess and other game programs, robots, et al. This decade the first presumably complete mathematical theory of artificial intelligence based on universal induction-prediction-decision-action has been proposed. This information-theoretic approach solidifies the foundations of inductive inference and artificial intelligence. Getting the foundations right usually marks a significant progress and maturing of a field. The theory provides a gold standard and guidance for researchers working on intelligent algorithms. The roots of universal induction have been laid exactly half-a-century ago and the roots of universal intelligence exactly one decade ago. So it is timely to take stock of what has been achieved and what remains to be done. Since there are already good recent surveys, I describe the state-of-the-art only in passing and refer the reader to the literature. This article concentrates on the open problems in universal induction and its extension to universal intelligence.
This paper is a survey of a large number of informal definitions of ``intelligence'' that the authors have collected over the years. Naturally, compiling a complete list would be impossible as many definitions of intelligence are buried deep inside articles and books. Nevertheless, the 70-odd definitions presented here are, to the authors' knowledge, the largest and most well referenced collection there is.
Data Mining techniques plays a vital role like extraction of required knowledge, finding unsuspected information to make strategic decision in a novel way which in term understandable by domain experts. A generalized frame work is proposed by considering non - domain experts during mining process for better understanding, making better decision and better finding new patters in case of selecting suitable data mining techniques based on the user profile by means of intelligent agents. KEYWORDS: Data Mining Techniques, Intelligent Agents, User Profile, Multidimensional Visualization, Knowledge Discovery.
Observing that the creation of certain types of artistic artifacts necessitate intelligence, we present the Lovelace 2.0 Test of creativity as an alternative to the Turing Test as a means of determining whether an agent is intelligent. The Lovelace 2.0 Test builds off prior tests of creativity and additionally provides a means of directly comparing the relative intelligence of different agents.
In the era of intelligent biohybrid neurotechnologies for brain repair, new fanciful terms are appearing in the scientific dictionary to define what has so far been unimaginable. As the emerging neurotechnologies are becoming increasingly polyhedral and sophisticated, should we talk about evolution and rank the intelligence of these devices?
This paper introduce a software system including widely-used Swarm Intelligence algorithms or approaches to be used for the related scientific research studies associated with the subject area. The programmatic infrastructure of the system allows working on a fast, easy-to-use, interactive platform to perform Swarm Intelligence based studies in a more effective, efficient and accurate way. In this sense, the system employs all of the necessary controls for the algorithms and it ensures an interactive platform on which computer users can perform studies on a wide spectrum of solution approaches associated with simple and also more advanced problems.
Turing test was long considered the measure for artificial intelligence. But with the advances in AI, it has proved to be insufficient measure. We can now aim to mea- sure machine intelligence like we measure human intelligence. One of the widely accepted measure of intelligence is standardized math and science test. In this paper, we explore the progress we have made towards the goal of making a machine smart enough to pass the standardized test. We see the challenges and opportunities posed by the domain, and note that we are quite some ways from actually making a system as smart as a even a middle school scholar.
Numerous, artificially intelligent, networked things will populate the battlefield of the future, operating in close collaboration with human warfighters, and fighting as teams in highly adversarial environments. This paper explores the characteristics, capabilities and intelligence required of such a network of intelligent things and humans - Internet of Battle Things (IOBT). It will experience unique challenges that are not yet well addressed by the current generation of AI and machine learning.
This paper presents an information theoretic approach to the concept of intelligence in the computational sense. We introduce a probabilistic framework from which computational intelligence is shown to be an entropy minimizing process at the local level. Using this new scheme, we develop a simple data driven clustering example and discuss its applications.
This paper proposes a model for combination of external and internal stimuli for the action selection in an autonomous agent, based in an action selection mechanism previously proposed by the authors. This combination model includes additive and multiplicative elements, which allows to incorporate new properties, which enhance the action selection. A given parameter a, which is part of the proposed model, allows to regulate the degree of dependence of the observed external behaviour from the internal states of the entity.
This paper investigates the use of different Artificial Intelligence methods to predict the values of several continuous variables from a Steam Generator. The objective was to determine how the different artificial intelligence methods performed in making predictions on the given dataset. The artificial intelligence methods evaluated were Neural Networks, Support Vector Machines, and Adaptive Neuro-Fuzzy Inference Systems. The types of neural networks investigated were Multi-Layer Perceptions, and Radial Basis Function. Bayesian and committee techniques were applied to these neural networks. Each of the AI methods considered was simulated in Matlab. The results of the simulations showed that all the AI methods were capable of predicting the Steam Generator data reasonably accurately. However, the Adaptive Neuro-Fuzzy Inference system out performed the other methods in terms of accuracy and ease of implementation, while still achieving a fast execution time as well as a reasonable training time.
Microarray is one of the essential technologies used by the biologist to measure genome-wide expression levels of genes in a particular organism under some particular conditions or stimuli. As microarrays technologies have become more prevalent, the challenges of analyzing these data for getting better insight about biological processes have essentially increased. Due to availability of artificial intelligence based sophisticated computational techniques, such as artificial neural networks, fuzzy logic, genetic algorithms, and many other nature-inspired algorithms, it is possible to analyse microarray gene expression data in more better way. Here, we reviewed artificial intelligence based techniques for the analysis of microarray gene expression data. Further, challenges in the field and future work direction have also been suggested.
The 7th Symposium on Educational Advances in Artificial Intelligence (EAAI'17, co-chaired by Sven Koenig and Eric Eaton) launched the EAAI New and Future AI Educator Program to support the training of early-career university faculty, secondary school faculty, and future educators (PhD candidates or postdocs who intend a career in academia). As part of the program, awardees were asked to address one of the following "blue sky" questions:   * How could/should Artificial Intelligence (AI) courses incorporate ethics into the curriculum?   * How could we teach AI topics at an early undergraduate or a secondary school level?   * AI has the potential for broad impact to numerous disciplines. How could we make AI education more interdisciplinary, specifically to benefit non-engineering fields?   This paper is a collection of their responses, intended to help motivate discussion around these issues in AI education.
Artificial intelligence methods have often been applied to perform specific functions or tasks in the cyber-defense realm. However, as adversary methods become more complex and difficult to divine, piecemeal efforts to understand cyber-attacks, and malware-based attacks in particular, are not providing sufficient means for malware analysts to understand the past, present and future characteristics of malware.   In this paper, we present the Malware Analysis and Attributed using Genetic Information (MAAGI) system. The underlying idea behind the MAAGI system is that there are strong similarities between malware behavior and biological organism behavior, and applying biologically inspired methods to corpora of malware can help analysts better understand the ecosystem of malware attacks. Due to the sophistication of the malware and the analysis, the MAAGI system relies heavily on artificial intelligence techniques to provide this capability. It has already yielded promising results over its development life, and will hopefully inspire more integration between the artificial intelligence and cyber--defense communities.
We consider the fundamental question: how a legacy "student" Artificial Intelligent (AI) system could learn from a legacy "teacher" AI system or a human expert without complete re-training and, most importantly, without requiring significant computational resources. Here "learning" is understood as an ability of one system to mimic responses of the other and vice-versa. We call such learning an Artificial Intelligence knowledge transfer. We show that if internal variables of the "student" Artificial Intelligent system have the structure of an $n$-dimensional topological vector space and $n$ is sufficiently high then, with probability close to one, the required knowledge transfer can be implemented by simple cascades of linear functionals. In particular, for $n$ sufficiently large, with probability close to one, the "student" system can successfully and non-iteratively learn $k\ll n$ new examples from the "teacher" (or correct the same number of mistakes) at the cost of two additional inner products. The concept is illustrated with an example of knowledge transfer from a pre-trained convolutional neural network to a simple linear classifier with HOG features.
We propose to use a supervised machine learning technique to track the location of a mobile agent in real time. Hidden Markov Models are used to build artificial intelligence that estimates the unknown position of a mobile target moving in a defined environment. This narrow artificial intelligence performs two distinct tasks. First, it provides real-time estimation of the mobile agent's position using the forward algorithm. Second, it uses the Baum-Welch algorithm as a statistical learning tool to gain knowledge of the mobile target. Finally, an experimental environment is proposed, namely a video game that we use to test our artificial intelligence. We present statistical and graphical results to illustrate the efficiency of our method.
The elusive quest for intelligence in artificial intelligence prompts us to consider that instituting human-level intelligence in systems may be (still) in the realm of utopia. In about a quarter century, we have witnessed the winter of AI (1990) being transformed and transported to the zenith of tabloid fodder about AI (2015). The discussion at hand is about the elements that constitute the canonical idea of intelligence. The delivery of intelligence as a pay-per-use-service, popping out of an app or from a shrink-wrapped software defined point solution, is in contrast to the bio-inspired view of intelligence as an outcome, perhaps formed from a tapestry of events, cross-pollinated by instances, each with its own microcosm of experiences and learning, which may not be discrete all-or-none functions but continuous, over space and time. The enterprise world may not require, aspire or desire such an engaged solution to improve its services for enabling digital transformation through the deployment of digital twins, for example. One might ask whether the "work-flow on steroids" version of decision support may suffice for intelligence? Are we harking back to the era of rule based expert systems? The image conjured by the publicity machines offers deep solutions with human-level AI and preposterous claims about capturing the "brain in a box" by 2020. Even emulating insects may be difficult in terms of real progress. Perhaps we can try to focus on worms (Caenorhabditis elegans) which may be better suited for what business needs to quench its thirst for so-called intelligence in AI.
This paper summarises how the "SP theory of intelligence" and its realisation in the "SP computer model" simplifies and integrates concepts across artificial intelligence and related areas, and thus provides a promising foundation for the development of a general, human-level thinking machine, in accordance with the main goal of research in artificial general intelligence.   The key to this simplification and integration is the powerful concept of "multiple alignment", borrowed and adapted from bioinformatics. This concept has the potential to be the "double helix" of intelligence, with as much significance for human-level intelligence as has DNA for biological sciences.   Strengths of the SP system include: versatility in the representation of diverse kinds of knowledge; versatility in aspects of intelligence (including: strengths in unsupervised learning; the processing of natural language; pattern recognition at multiple levels of abstraction that is robust in the face of errors in data; several kinds of reasoning (including: one-step `deductive' reasoning; chains of reasoning; abductive reasoning; reasoning with probabilistic networks and trees; reasoning with 'rules'; nonmonotonic reasoning and reasoning with default values; Bayesian reasoning with 'explaining away'; and more); planning; problem solving; and more); seamless integration of diverse kinds of knowledge and diverse aspects of intelligence in any combination; and potential for application in several areas (including: helping to solve nine problems with big data; helping to develop human-level intelligence in autonomous robots; serving as a database with intelligence and with versatility in the representation and integration of several forms of knowledge; serving as a vehicle for medical knowledge and as an aid to medical diagnosis; and several more).
The SP theory of computing and cognition, described in previous publications, is an attractive model for intelligent databases because it provides a simple but versatile format for different kinds of knowledge, it has capabilities in artificial intelligence, and it can also function like established database models when that is required.   This paper describes how the SP model can emulate other models used in database applications and compares the SP model with those other models. The artificial intelligence capabilities of the SP model are reviewed and its relationship with other artificial intelligence systems is described. Also considered are ways in which current prototypes may be translated into an 'industrial strength' working system.
Since the Turing test was first proposed by Alan Turing in 1950, the primary goal of artificial intelligence has been predicated on the ability for computers to imitate human behavior. However, the majority of uses for the computer can be said to fall outside the domain of human abilities and it is exactly outside of this domain where computers have demonstrated their greatest contribution to intelligence. Another goal for artificial intelligence is one that is not predicated on human mimicry, but instead, on human amplification. This article surveys various systems that contribute to the advancement of human and social intelligence.
People sometimes worry about the Singularity [Vinge, 1993; Kurzweil, 2005], or about the world being taken over by artificially intelligent robots. I believe the risks of these are very small. However, few people recognize that we already share our world with artificial creatures that participate as intelligent agents in our society: corporations. Our planet is inhabited by two distinct kinds of intelligent beings --- individual humans and corporate entities --- whose natures and interests are intimately linked. To co-exist well, we need to find ways to define the rights and responsibilities of both individual humans and corporate entities, and to find ways to ensure that corporate entities behave as responsible members of society.
Reinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be interpreted as the agent's estimate of the probability of its death. We formally define death for generally intelligent agents like AIXI, and prove a number of related theorems about their behaviour. Notable discoveries include that agent behaviour can change radically under positive linear transformations of the reward signal (from suicidal to dogmatically self-preserving), and that the agent's posterior belief that it will survive increases over time.
Artificial General Intelligence is a field of research aiming to distill the principles of intelligence that operate independently of a specific problem domain or a predefined context and utilize these principles in order to synthesize systems capable of performing any intellectual task a human being is capable of and eventually go beyond that. While "narrow" artificial intelligence which focuses on solving specific problems such as speech recognition, text comprehension, visual pattern recognition, robotic motion, etc. has shown quite a few impressive breakthroughs lately, understanding general intelligence remains elusive. In the paper we offer a novel theoretical approach to understanding general intelligence. We start with a brief introduction of the current conceptual approach. Our critique exposes a number of serious limitations that are traced back to the ontological roots of the concept of intelligence. We then propose a paradigm shift from intelligence perceived as a competence of individual agents defined in relation to an a priori given problem domain or a goal, to intelligence perceived as a formative process of self-organization by which intelligent agents are individuated. We call this process open-ended intelligence. Open-ended intelligence is developed as an abstraction of the process of cognitive development so its application can be extended to general agents and systems. We introduce and discuss three facets of the idea: the philosophical concept of individuation, sense-making and the individuation of general cognitive agents. We further show how open-ended intelligence can be framed in terms of a distributed, self-organizing network of interacting elements and how such process is scalable. The framework highlights an important relation between coordination and intelligence and a new understanding of values. We conclude with a number of questions for future research.
This article deals with the links between the enaction paradigm and artificial intelligence. Enaction is considered a metaphor for artificial intelligence, as a number of the notions which it deals with are deemed incompatible with the phenomenal field of the virtual. After explaining this stance, we shall review previous works regarding this issue in terms of artifical life and robotics. We shall focus on the lack of recognition of co-evolution at the heart of these approaches. We propose to explicitly integrate the evolution of the environment into our approach in order to refine the ontogenesis of the artificial system, and to compare it with the enaction paradigm. The growing complexity of the ontogenetic mechanisms to be activated can therefore be compensated by an interactive guidance system emanating from the environment. This proposition does not however resolve that of the relevance of the meaning created by the machine (sense-making). Such reflections lead us to integrate human interaction into this environment in order to construct relevant meaning in terms of participative artificial intelligence. This raises a number of questions with regards to setting up an enactive interaction. The article concludes by exploring a number of issues, thereby enabling us to associate current approaches with the principles of morphogenesis, guidance, the phenomenology of interactions and the use of minimal enactive interfaces in setting up experiments which will deal with the problem of artificial intelligence in a variety of enaction-based ways.
Sequential decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameter-free theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI model is the most intelligent unbiased agent possible. We outline how the AIXI model can formally solve a number of problem classes, including sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXItl that is still effectively more intelligent than any other time t and length l bounded agent. The computation time of AIXItl is of the order t x 2^l. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches.
Our understanding of intelligence is directed primarily at the level of human beings. This paper attempts to give a more unifying definition that can be applied to the natural world in general. The definition would be used more to verify a degree of intelligence, not to quantify it and might help when making judgements on the matter. A version of an accepted test for AI is then put forward as the 'acid test' for Artificial Intelligence itself. It might be what a free-thinking program or robot would try to achieve. Recent work by the author on AI has been more from a direction of mechanical processes, or ones that might operate automatically. This paper will not try to question the idea of intelligence, in the sense of a pro-active or conscious event, but try to put it into a more passive, automatic and mechanical context. The paper also suggests looking at intelligence and consciousness as being slightly different.
This paper looks at Turing's postulations about Artificial Intelligence in his paper 'Computing Machinery and Intelligence', published in 1950. It notes how accurate they were and how relevant they still are today. This paper notes the arguments and mechanisms that he suggested and tries to expand on them further. The paper however is mostly about describing the essential ingredients for building an intelligent model and the problems related with that. The discussion includes recent work by the author himself, who adds his own thoughts on the matter that come from a purely technical investigation into the problem. These are personal and quite speculative, but provide an interesting insight into the mechanisms that might be used for building an intelligent system.
There is overwhelming evidence that human intelligence is a product of Darwinian evolution. Investigating the consequences of self-modification, and more precisely, the consequences of utility function self-modification, leads to the stronger claim that not only human, but any form of intelligence is ultimately only possible within evolutionary processes. Human-designed artificial intelligences can only remain stable until they discover how to manipulate their own utility function. By definition, a human designer cannot prevent a superhuman intelligence from modifying itself, even if protection mechanisms against this action are put in place. Without evolutionary pressure, sufficiently advanced artificial intelligences become inert by simplifying their own utility function. Within evolutionary processes, the implicit utility function is always reducible to persistence, and the control of superhuman intelligences embedded in evolutionary processes is not possible. Mechanisms against utility function self-modification are ultimately futile. Instead, scientific effort toward the mitigation of existential risks from the development of superintelligences should be in two directions: understanding consciousness, and the complex dynamics of evolutionary systems.
In Intelligence Analysis it is of vital importance to manage uncertainty. Intelligence data is almost always uncertain and incomplete, making it necessary to reason and taking decisions under uncertainty. One way to manage the uncertainty in Intelligence Analysis is Dempster-Shafer Theory. This thesis contains five results regarding multiple target tracks and intelligence specification.
In this paper we develop an evidential force aggregation method intended for classification of evidential intelligence into recognized force structures. We assume that the intelligence has already been partitioned into clusters and use the classification method individually in each cluster. The classification is based on a measure of fitness between template and fused intelligence that makes it possible to handle intelligence reports with multiple nonspecific and uncertain propositions. With this measure we can aggregate on a level-by-level basis, starting from general intelligence to achieve a complete force structure with recognized units on all hierarchical levels.
Similar to intelligent multicellular neural networks controlling human brains, even single cells surprisingly are able to make intelligent decisions to classify several external stimuli or to associate them. This happens because of the fact that gene regulatory networks can perform as perceptrons, simple intelligent schemes known from studies on Artificial Intelligence. We study the role of genetic noise in intelligent decision making at the genetic level and show that noise can play a constructive role helping cells to make a proper decision. We show this using the example of a simple genetic classifier able to classify two external stimuli.
This paper assumes the hypothesis that human learning is perception based, and consequently, the learning process and perceptions should not be represented and investigated independently or modeled in different simulation spaces. In order to keep the analogy between the artificial and human learning, the former is assumed here as being based on the artificial perception. Hence, instead of choosing to apply or develop a Computational Theory of (human) Perceptions, we choose to mirror the human perceptions in a numeric (computational) space as artificial perceptions and to analyze the interdependence between artificial learning and artificial perception in the same numeric space, using one of the simplest tools of Artificial Intelligence and Soft Computing, namely the perceptrons. As practical applications, we choose to work around two examples: Optical Character Recognition and Iris Recognition. In both cases a simple Turing test shows that artificial perceptions of the difference between two characters and between two irides are fuzzy, whereas the corresponding human perceptions are, in fact, crisp.
Today, available methods that assess AI systems are focused on using empirical techniques to measure the performance of algorithms in some specific tasks (e.g., playing chess, solving mazes or land a helicopter). However, these methods are not appropriate if we want to evaluate the general intelligence of AI and, even less, if we compare it with human intelligence. The ANYNT project has designed a new method of evaluation that tries to assess AI systems using well known computational notions and problems which are as general as possible. This new method serves to assess general intelligence (which allows us to learn how to solve any new kind of problem we face) and not only to evaluate performance on a set of specific tasks. This method not only focuses on measuring the intelligence of algorithms, but also to assess any intelligent system (human beings, animals, AI, aliens?,...), and letting us to place their results on the same scale and, therefore, to be able to compare them. This new approach will allow us (in the future) to evaluate and compare any kind of intelligent system known or even to build/find, be it artificial or biological. This master thesis aims at ensuring that this new method provides consistent results when evaluating AI algorithms, this is done through the design and implementation of prototypes of universal intelligence tests and their application to different intelligent systems (AI algorithms and humans beings). From the study we analyze whether the results obtained by two different intelligent systems are properly located on the same scale and we propose changes and refinements to these prototypes in order to, in the future, being able to achieve a truly universal intelligence test.
OPUS is a branch and bound search algorithm that enables efficient admissible search through spaces for which the order of search operator application is not significant. The algorithm's search efficiency is demonstrated with respect to very large machine learning search spaces. The use of admissible search is of potential value to the machine learning community as it means that the exact learning biases to be employed for complex learning tasks can be precisely specified and manipulated. OPUS also has potential for application in other areas of artificial intelligence, notably, truth maintenance.
This paper applies resolution theorem proving to natural language semantics. The aim is to circumvent the computational complexity triggered by natural language ambiguities like pronoun binding, by interleaving pronoun binding with resolution deduction. Therefore disambiguation is only applied to expression that actually occur during derivations.
We introduce a logic for reasoning about evidence that essentially views evidence as a function from prior beliefs (before making an observation) to posterior beliefs (after making the observation). We provide a sound and complete axiomatization for the logic, and consider the complexity of the decision problem. Although the reasoning in the logic is mainly propositional, we allow variables representing numbers and quantification over them. This expressive power seems necessary to capture important properties of evidence.
This paper overviews the basic principles and recent advances in the emerging field of Quantum Computation (QC), highlighting its potential application to Artificial Intelligence (AI). The paper provides a very brief introduction to basic QC issues like quantum registers, quantum gates and quantum algorithms and then it presents references, ideas and research guidelines on how QC can be used to deal with some basic AI problems, such as search and pattern matching, as soon as quantum computers become widely available.
In a certain number of situations, human cognitive functioning is difficult to represent with classical artificial intelligence structures. Such a difficulty arises in the polyneuropathy diagnosis which is based on the spatial distribution, along the nerve fibres, of lesions, together with the synthesis of several partial diagnoses. Faced with this problem while building up an expert system (NEUROP), we developed a heterogeneous knowledge representation associating a finite automaton with first order logic. A number of knowledge representation problems raised by the electromyography test features are examined in this study and the expert system architecture allowing such a knowledge modeling are laid out.
In Pe\~na (2007), MCMC sampling is applied to approximately calculate the ratio of essential graphs (EGs) to directed acyclic graphs (DAGs) for up to 20 nodes. In the present paper, we extend that work from 20 to 31 nodes. We also extend that work by computing the approximate ratio of connected EGs to connected DAGs, of connected EGs to EGs, and of connected DAGs to DAGs. Furthermore, we prove that the latter ratio is asymptotically 1. We also discuss the implications of these results for learning DAGs from data.
We examine the computational complexity of testing and finding small plans in probabilistic planning domains with succinct representations. We find that many problems of interest are complete for a variety of complexity classes: NP, co-NP, PP, NP^PP, co-NP^PP, and PSPACE. Of these, the probabilistic classes PP and NP^PP are likely to be of special interest in the field of uncertainty in artificial intelligence and are deserving of additional study. These results suggest a fruitful direction of future algorithmic development.
Probabilistic conceptual network is a knowledge representation scheme designed for reasoning about concepts and categorical abstractions in utility-based categorization. The scheme combines the formalisms of abstraction and inheritance hierarchies from artificial intelligence, and probabilistic networks from decision analysis. It provides a common framework for representing conceptual knowledge, hierarchical knowledge, and uncertainty. It facilitates dynamic construction of categorization decision models at varying levels of abstraction. The scheme is applied to an automated machining problem for reasoning about the state of the machine at varying levels of abstraction in support of actions for maintaining competitiveness of the plant.
Evidential reasoning is now a leading topic in Artificial Intelligence. Evidence is represented by a variety of evidential functions. Evidential reasoning is carried out by certain kinds of fundamental operation on these functions. This paper discusses two of the basic operations on evidential functions, the discount operation and the well-known orthogonal sum operation. We show that the discount operation is not commutative with the orthogonal sum operation, and derive expressions for the two operations applied to the various evidential function.
We present initial ideas for a programming paradigm based on simulation that is targeted towards applications of artificial intelligence (AI). The approach aims at integrating techniques from different areas of AI and is based on the idea that simulated entities may freely exchange data and behavioural patterns. We define basic notions of a simulation-based programming paradigm and show how it can be used for implementing AI applications.
This paper describes the incorporation of uncertainty in diagnostic reasoning based on the set covering model of Reggia et. al. extended to what in the Artificial Intelligence dichotomy between deep and compiled (shallow, surface) knowledge based diagnosis may be viewed as the generic form at the compiled end of the spectrum. A major undercurrent in this is advocating the need for a strong underlying model and an integrated set of support tools for carrying such a model in order to deal with uncertainty.
Various properties of relative entropy have led to its widespread use in information theory. These properties suggest that relative entropy has a role to play in systems that attempt to perform inference in terms of probability distributions. In this paper, I will review some basic properties of relative entropy as well as its role in probabilistic inference. I will also mention briefly a few existing and potential applications of relative entropy to so-called artificial intelligence (AI).
In the field of Artificial Intelligence, traditional approaches to choosing moves in games involve the we of the minimax algorithm. However, recent research results indicate that minimizing may not always be the best approach. In this paper we summarize the results of some measurements on several model games with several different evaluation functions. These measurements, which are presented in detail in [NPT], show that there are some new algorithms that can make significantly better use of evaluation function values than the minimax algorithm does.
Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.
This paper considers the computational power of constant size, dynamic Bayesian networks. Although discrete dynamic Bayesian networks are no more powerful than hidden Markov models, dynamic Bayesian networks with continuous random variables and discrete children of continuous parents are capable of performing Turing-complete computation. With modified versions of existing algorithms for belief propagation, such a simulation can be carried out in real time. This result suggests that dynamic Bayesian networks may be more powerful than previously considered. Relationships to causal models and recurrent neural networks are also discussed.
In recent years prominent intellectuals have raised ethical concerns about the consequences of artificial intelligence. One concern is that an autonomous agent might modify itself to become "superintelligent" and, in supremely effective pursuit of poorly specified goals, destroy all of humanity. This paper considers and rejects the possibility of this outcome. We argue that this scenario depends on an agent's ability to rapidly improve its ability to predict its environment through self-modification. Using a Bayesian model of a reasoning agent, we show that there are important limitations to how an agent may improve its predictive ability through self-modification alone. We conclude that concern about this artificial intelligence outcome is misplaced and better directed at policy questions around data access and storage.
General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.
Multi-agent path finding (MAPF) is a well-studied problem in artificial intelligence, where one needs to find collision-free paths for agents with given start and goal locations. In video games, agents of different types often form teams. In this paper, we demonstrate the usefulness of MAPF algorithms from artificial intelligence for moving such non-homogeneous teams in congested video game environments.
Here we examine the paperclip apocalypse concern for artificial general intelligence (or AGI) whereby a superintelligent AI with a simple goal (ie., producing paperclips) accumulates power so that all resources are devoted towards that simple goal and are unavailable for any other use. We provide conditions under which a paper apocalypse can arise but also show that, under certain architectures for recursive self-improvement of AIs, that a paperclip AI may refrain from allowing power capabilities to be developed. The reason is that such developments pose the same control problem for the AI as they do for humans (over AIs) and hence, threaten to deprive it of resources for its primary goal.
The welfare of modern societies has been intrinsically linked to wage labour. With some exceptions, the modern human has to sell her labour-power to be able reproduce biologically and socially. Thus, a lingering fear of technological unemployment features predominately as a theme among Artificial Intelligence researchers. In this short paper we show that, if past trends are anything to go by, this fear is irrational. On the contrary, we argue that the main problem humanity will be facing is the normalisation of extremely long working hours.
One of the main research areas in Artificial Intelligence is the coding of agents (programs) which are able to learn by themselves in any situation. This means that agents must be useful for purposes other than those they were created for, as, for example, playing chess. In this way we try to get closer to the pristine goal of Artificial Intelligence. One of the problems to decide whether an agent is really intelligent or not is the measurement of its intelligence, since there is currently no way to measure it in a reliable way. The purpose of this project is to create an interpreter that allows for the execution of several environments, including those which are generated randomly, so that an agent (a person or a program) can interact with them. Once the interaction between the agent and the environment is over, the interpreter will measure the intelligence of the agent according to the actions, states and rewards the agent has undergone inside the environment during the test. As a result we will be able to measure agents' intelligence in any possible environment, and to make comparisons between several agents, in order to determine which of them is the most intelligent. In order to perform the tests, the interpreter must be able to randomly generate environments that are really useful to measure agents' intelligence, since not any randomly generated environment will serve that purpose.
Efficiently entering information into a computer is key to enjoying the benefits of computing. This paper describes three intelligent user interfaces: handwriting recognition, adaptive menus, and predictive fillin. In the context of adding a personUs name and address to an electronic organizer, tests show handwriting recognition is slower than typing on an on-screen, soft keyboard, while adaptive menus and predictive fillin can be twice as fast. This paper also presents strategies for applying these three interfaces to other information collection domains.
How can we design good goals for arbitrarily intelligent agents? Reinforcement learning (RL) is a natural approach. Unfortunately, RL does not work well for generally intelligent agents, as RL agents are incentivised to shortcut the reward sensor for maximum reward -- the so-called wireheading problem. In this paper we suggest an alternative to RL called value reinforcement learning (VRL). In VRL, agents use the reward signal to learn a utility function. The VRL setup allows us to remove the incentive to wirehead by placing a constraint on the agent's actions. The constraint is defined in terms of the agent's belief distributions, and does not require an explicit specification of which actions constitute wireheading.
Although the problem of a critique of robotic behavior in near-unanimous agreement to human norms seems intractable, a starting point of such an ambition is a framework of the collection of knowledge a priori and experience a posteriori categorized as a set of synthetical judgments available to the intelligence, translated into computer code. If such a proposal were successful, an algorithm with ethically traceable behavior and cogent equivalence to human cognition is established. This paper will propose the application of Kant's critique of reason to current programming constructs of an autonomous intelligent system.
Theoretical analysis of machine intelligence (MI) is useful for defining a common platform in both theoretical and applied artificial intelligence (AI). The goal of this paper is to set canonical definitions that can assist pragmatic research in both strong and weak AI. Described epistemological features of machine intelligence include relationship between intelligent behavior, intelligent and unintelligent machine characteristics, observable and unobservable entities and classification of intelligence. The paper also establishes algebraic definitions of efficiency and accuracy of MI tests as their quality measure. The last part of the paper addresses the learning process with respect to the traditional epistemology and the epistemology of MI described here. The proposed views on MI positively correlate to the Hegelian monistic epistemology and contribute towards amalgamating idealistic deliberations with the AI theory, particularly in a local frame of reference.
A definition of Artificial Intelligence was proposed in [1] but this definition was not absolutely formal at least because the word "Human" was used. In this paper we will formalize the definition from [1]. The biggest problem in this definition was that the level of intelligence of AI is compared to the intelligence of a human being. In order to change this we will introduce some parameters to which AI will depend. One of this parameters will be the level of intelligence and we will define one AI to each level of intelligence. We assume that for some level of intelligence the respective AI will be more intelligent than a human being. Nevertheless, we cannot say which is this level because we cannot calculate its exact value.
Stream computing is the use of multiple autonomic and parallel modules together with integrative processors at a higher level of abstraction to embody "intelligent" processing. The biological basis of this computing is sketched and the matter of learning is examined.
In this article, we describe the fuzzy logic, fuzzy language and algorithms as the basis of fuzzy reasoning, one of the intelligent information processing method, and then describe the general fuzzy reasoning method.
The vision systems of the eagle and the snake outperform everything that we can make in the laboratory, but snakes and eagles cannot build an eyeglass or a telescope or a microscope. (Judea Pearl)
Artificial Chemistries (ACs) are symbolic chemical metaphors for the exploration of Artificial Life, with specific focus on the origin of life. In this work we define a P system based artificial graph chemistry to understand the principles leading to the evolution of life-like structures in an AC set up and to develop a unified framework to characterize and classify symbolic artificial chemistries by devising appropriate formalism to capture semantic and organizational information. An extension of P system is considered by associating probabilities with the rules providing the topological framework for the evolution of a labeled undirected graph based molecular reaction semantics.
Research on human self-regulation has shown that people hold many goals simultaneously and have complex self-regulation mechanisms to deal with this goal conflict. Artificial autonomous systems may also need to find ways to cope with conflicting goals. Indeed, the intricate interplay among different goals may be critical to the design as well as long-term safety and stability of artificial autonomous systems. I discuss some of the critical features of the human self-regulation system and how it might be applied to an artificial system. Furthermore, the implications of goal conflict for the reliability and stability of artificial autonomous systems and ensuring their alignment with human goals and ethics is examined.
With the advances in information technology (IT) criminals are using cyberspace to commit numerous cyber crimes. Cyber infrastructures are highly vulnerable to intrusions and other threats. Physical devices and human intervention are not sufficient for monitoring and protection of these infrastructures; hence, there is a need for more sophisticated cyber defense systems that need to be flexible, adaptable and robust, and able to detect a wide variety of threats and make intelligent real-time decisions. Numerous bio-inspired computing methods of Artificial Intelligence have been increasingly playing an important role in cyber crime detection and prevention. The purpose of this study is to present advances made so far in the field of applying AI techniques for combating cyber crimes, to demonstrate how these techniques can be an effective tool for detection and prevention of cyber attacks, as well as to give the scope for future work.
In this paper, the idea of a new artificial intelligence based optimization algorithm, which is inspired from the nature of vortex, has been provided briefly. As also a bio-inspired computation algorithm, the idea is generally focused on a typical vortex flow / behavior in nature and inspires from some dynamics that are occurred in the sense of vortex nature. Briefly, the algorithm is also a swarm-oriented evolutional problem solution approach; because it includes many methods related to elimination of weak swarm members and trying to improve the solution process by supporting the solution space via new swarm members. In order have better idea about success of the algorithm; it has been tested via some benchmark functions. At this point, the obtained results show that the algorithm can be an alternative to the literature in terms of single-objective optimization solution ways. Vortex Optimization Algorithm (VOA) is the name suggestion by the authors; for this new idea of intelligent optimization approach.
Decomposable dependency models possess a number of interesting and useful properties. This paper presents new characterizations of decomposable models in terms of independence relationships, which are obtained by adding a single axiom to the well-known set characterizing dependency models that are isomorphic to undirected graphs. We also briefly discuss a potential application of our results to the problem of learning graphical models from data.
A general notion of algebraic conditional plausibility measures is defined. Probability measures, ranking functions, possibility measures, and (under the appropriate definitions) sets of probability measures can all be viewed as defining algebraic conditional plausibility measures. It is shown that algebraic conditional plausibility measures can be represented using Bayesian networks.
This paper presents a review of instantaneously trained neural networks (ITNNs). These networks trade learning time for size and, in the basic model, a new hidden node is created for each training sample. Various versions of the corner-classification family of ITNNs, which have found applications in artificial intelligence (AI), are described. Implementation issues are also considered.
In game theory and artificial intelligence, decision making models often involve maximizing expected utility, which does not respect ordinal invariance. In this paper, the author discusses the possibility of preserving ordinal invariance and still making a rational decision under uncertainty.
Neurons are individually translated into simple gates to plan a brain based on human psychology and intelligence. State machines, assumed previously learned in subconscious associative memory are shown to enable equation solving and rudimentary thinking using nanoprocessing within short term memory.
I consider the problem of learning an optimal path graphical model from data and show the problem to be NP-hard for the maximum likelihood and minimum description length approaches and a Bayesian approach. This hardness result holds despite the fact that the problem is a restriction of the polynomially solvable problem of finding the optimal tree graphical model.
The SHOP2 planning system received one of the awards for distinguished performance in the 2002 International Planning Competition. This paper describes the features of SHOP2 which enabled it to excel in the competition, especially those aspects of SHOP2 that deal with temporal and metric planning domains.
We address the problem of propositional logic-based abduction, i.e., the problem of searching for a best explanation for a given propositional observation according to a given propositional knowledge base. We give a general algorithm, based on the notion of projection; then we study restrictions over the representations of the knowledge base and of the query, and find new polynomial classes of abduction problems.
Artificial general intelligence aims to create agents capable of learning to solve arbitrary interesting problems. We define two versions of asymptotic optimality and prove that no agent can satisfy the strong version while in some cases, depending on discounting, there does exist a non-computable weak asymptotically optimal agent.
We present a partial-order, conformant, probabilistic planner, Probapop which competed in the blind track of the Probabilistic Planning Competition in IPC-4. We explain how we adapt distance based heuristics for use with probabilistic domains. Probapop also incorporates heuristics based on probability of success. We explain the successes and difficulties encountered during the design and implementation of Probapop.
Acyclic directed mixed graphs, also known as semi-Markov models represent the conditional independence structure induced on an observed margin by a DAG model with latent variables. In this paper we present the first method for fitting these models to binary data using maximum likelihood estimation.
This paper addresses the problem of measurement errors in causal inference and highlights several algebraic and graphical methods for eliminating systematic bias induced by such errors. In particulars, the paper discusses the control of partially observable confounders in parametric and non parametric models and the computational problem of obtaining bias-free effect estimates in such models.
Symmetry is an important problem in many combinatorial problems. One way of dealing with symmetry is to add constraints that eliminate symmetric solutions. We survey recent results in this area, focusing especially on two common and useful cases: symmetry breaking constraints for row and column symmetry, and symmetry breaking constraints for eliminating value symmetry
This paper presents complexity analysis and variational methods for inference in probabilistic description logics featuring Boolean operators, quantification, qualified number restrictions, nominals, inverse roles and role hierarchies. Inference is shown to be PEXP-complete, and variational methods are designed so as to exploit logical inference whenever possible.
We address the problem of identifying dynamic sequential plans in the framework of causal Bayesian networks, and show that the problem is reduced to identifying causal effects, for which there are complete identi cation algorithms available in the literature.
We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictive.
This paper deals with the problem of identifying direct causal effects in recursive linear structural equation models. The paper establishes a sufficient criterion for identifying individual causal effects and provides a procedure computing identified causal effects in terms of observed covariance matrix.
We derive novel sufficient conditions for convergence of Loopy Belief Propagation (also known as the Sum-Product algorithm) to a unique fixed point. Our results improve upon previously known conditions. For binary variables with (anti-)ferromagnetic interactions, our conditions seem to be sharp.
We present a fuzzy version of description logics with concrete domains. Main features are: (i) concept constructors are based on t-norm, t-conorm, negation and implication; (ii) concrete domains are fuzzy sets; (iii) fuzzy modifiers are allowed; and (iv) the reasoning algorithm is based on a mixture of completion rules and bounded mixed integer programming.
We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.
We formulate necessary and sufficient conditions for an arbitrary discrete probability distribution to factor according to an undirected graphical model, or a log-linear model, or other more general exponential models. This result generalizes the well known Hammersley-Clifford Theorem.
We are interested in the problem of planning for factored POMDPs. Building on the recent results of Kearns, Mansour and Ng, we provide a planning algorithm for factored POMDPs that exploits the accuracy-efficiency tradeoff in the belief state simplification introduced by Boyen and Koller.
A control algorithm for batch processing of mixed waste is proposed based on conditional Gaussian Bayesian networks. The network is compiled during batch staging for real-time response to sensor input.
In the last decade, several architectures have been proposed for exact computation of marginals using local computation. In this paper, we compare three architectures - Lauritzen-Spiegelhalter, Hugin, and Shenoy-Shafer - from the perspective of graphical structure for message propagation, message-passing scheme, computational efficiency, and storage efficiency.
There is much interest in using partially observable Markov decision processes (POMDPs) as a formal model for planning in stochastic domains. This paper is concerned with finding optimal policies for POMDPs. We propose several improvements to incremental pruning, presently the most efficient exact algorithm for solving POMDPs.
A modelling language is described which is suitable for the correlation of information when the underlying functional model of the system is incomplete or uncertain and the temporal dependencies are imprecise. An efficient and incremental implementation is outlined which depends on cost functions satisfying certain criteria. Possibilistic logic and probability theory (as it is used in the applications targetted) satisfy these criteria.
This paper describes a class of probabilistic approximation algorithms based on bucket elimination which offer adjustable levels of accuracy and efficiency. We analyze the approximation for several tasks: finding the most probable explanation, belief updating and finding the maximum a posteriori hypothesis. We identify regions of completeness and provide preliminary empirical evaluation on randomly generated networks.
Poole has shown that nonmonotonic logics do not handle the lottery paradox correctly. In this paper we will show that Pollock's theory of defeasible reasoning fails for the same reason: defeasible reasoning is incompatible with the skeptical notion of derivability.
A stable joint plan should guarantee the achievement of a designer's goal in a multi-agent environment, while ensuring that deviations from the prescribed plan would be detected. We present a computational framework where stable joint plans can be studied, as well as several basic results about the representation, verification and synthesis of stable joint plans.
This paper is concerned with planning in stochastic domains by means of partially observable Markov decision processes (POMDPs). POMDPs are difficult to solve. This paper identifies a subclass of POMDPs called region observable POMDPs, which are easier to solve and can be used to approximate general POMDPs to arbitrary accuracy.
Lower and upper probabilities, also known as Choquet capacities, are widely used as a convenient representation for sets of probability distributions. This paper presents a graphical decomposition and exact propagation algorithm for computing marginal posteriors of 2-monotone lower probabilities (equivalently, 2-alternating upper probabilities).
In this paper we propose a family of algorithms combining tree-clustering with conditioning that trade space for time. Such algorithms are useful for reasoning in probabilistic and deterministic networks as well as for accomplishing optimization tasks. By analyzing the problem structure it will be possible to select from a spectrum the algorithm that best meets a given time-space specification.
We present deterministic techniques for computing upper and lower bounds on marginal probabilities in sigmoid and noisy-OR networks. These techniques become useful when the size of the network (or clique size) precludes exact computations. We illustrate the tightness of the bounds by numerical experiments.
The main goal of this paper is to describe a data structure called binary join trees that are useful in computing multiple marginals efficiently using the Shenoy-Shafer architecture. We define binary join trees, describe their utility, and sketch a procedure for constructing them.
For real time evaluation of a Bayesian network when there is not sufficient time to obtain an exact solution, a guaranteed response time, approximate solution is required. It is shown that nontraditional methods utilizing estimators based on an archive of trial solutions and genetic search can provide an approximate solution that is considerably superior to the traditional Monte Carlo simulation methods.
We provide a new characterization of the Dirichlet distribution. This characterization implies that under assumptions made by several previous authors for learning belief networks, a Dirichlet prior on the parameters is inevitable.
This is a working paper summarizing results of an ongoing research project whose aim is to uniquely characterize the uncertainty measure for the Dempster-Shafer Theory. A set of intuitive axiomatic requirements is presented, some of their implications are shown, and the proof is given of the minimality of recently proposed measure AU among all measures satisfying the proposed requirements.
This paper presents correct algorithms for answering the following two questions; (i) Does there exist a causal explanation consistent with a set of background knowledge which explains all of the observed independence facts in a sample? (ii) Given that there is such a causal explanation what are the causal relationships common to every such causal explanation?
A completeness result for d-separation applied to discrete Bayesian networks is presented and it is shown that in a strong measure-theoretic sense almost all discrete distributions for a given network structure are faithful; i.e. the independence facts true of the distribution are all and only those entailed by the network structure.
We develop a new semantics for defeasible inference based on extended probability measures allowed to take infinitesimal values, on the interpretation of defaults as generalized conditional probability constraints and on a preferred-model implementation of entropy maximization.
This paper examines the "K2" network scoring metric of Cooper and Herskovits. It shows counterintuitive results from applying this metric to simple networks. One family of noninformative priors is suggested for assigning equal scores to equivalent networks.
We propose an integration of possibility theory into non-classical logics. We obtain many formal results that generalize the case where possibility and necessity functions are based on classical logic. We show how useful such an approach is by applying it to reasoning under uncertain and inconsistent information.
We present an approach to the solution of decision problems formulated as influence diagrams. This approach involves a special triangulation of the underlying graph, the construction of a junction tree with special properties, and a message passing algorithm operating on the junction tree for computation of expected utilities and optimal decision policies.
We construct the belief function that quantifies the agent, beliefs about which event of Q will occurred when he knows that the event is selected by a chance set-up and that the probability function associated to the chance set up is only partially known.
This paper studies the connection between probabilistic conditional independence in uncertain reasoning and data dependency in relational databases. As a demonstration of the usefulness of this preliminary investigation, an alternate proof is presented for refuting the conjecture suggested by Pearl and Paz that probabilistic conditional independencies have a complete axiomatization.
This paper describes a normative system design that incorporates diagnosis, dynamic evolution, decision making, and information gathering. A single influence diagram demonstrates the design's coherence, yet each activity is more effectively modeled and evaluated separately. Application to offshore oil platforms illustrates the design. For this application, the normative system is embedded in a real-time expert system.
Two algorithms are presented for "compiling" influence diagrams into a set of simple decision rules. These decision rules define simple-to-execute, complete, consistent, and near-optimal decision procedures. These compilation algorithms can be used to derive decision procedures for human teams solving time constrained decision problems.
In order to find a causal explanation for data presented in the form of covariance and concentration matrices it is necessary to decide if the graph formed by such associations is a projection of a directed acyclic graph (dag). We show that the general problem of deciding whether such a dag exists is NP-complete.
This paper introduces a qualitative measure of ambiguity and analyses its relationship with other measures of uncertainty. Probability measures relative likelihoods, while ambiguity measures vagueness surrounding those judgments. Ambiguity is an important representation of uncertain knowledge. It deals with a different, type of uncertainty modeled by subjective probability or belief.
Jeffrey's rule of conditioning has been proposed in order to revise a probability measure by another probability function. We generalize it within the framework of the models based on belief functions. We show that several forms of Jeffrey's conditionings can be defined that correspond to the geometrical rule of conditioning and to Dempster's rule of conditioning, respectively.
In this paper, the concept of possibilistic evidence which is a possibility distribution as well as a body of evidence is proposed over an infinite universe of discourse. The inference with possibilistic evidence is investigated based on a unified inference framework maintaining both the compatibility of concepts and the consistency of the probability logic.
The product expansion of conditional probabilities for belief nets is not maximum entropy. This appears to deny a desirable kind of assurance for the model. However, a kind of guarantee that is almost as strong as maximum entropy can be derived. Surprisingly, a variant model also exhibits the guarantee, and for many cases obtains a higher performance score than the product expansion.
This paper introduces the notion of objection-based causal networks which resemble probabilistic causal networks except that they are quantified using objections. An objection is a logical sentence and denotes a condition under which a, causal dependency does not exist. Objection-based causal networks enjoy almost all the properties that make probabilistic causal networks popular, with the added advantage that objections are, arguably more intuitive than probabilities.
A new entropy-like measure as well as a new measure of total uncertainty pertaining to the Dempster-Shafer theory are introduced. It is argued that these measures are better justified than any of the previously proposed candidates.
We propose a general Bayesian network model for application in a wide class of problems of therapy monitoring. We discuss the use of stochastic simulation as a computational approach to inference on the proposed class of models. As an illustration we present an application to the monitoring of cytotoxic chemotherapy in breast cancer.
Useless paths are a chronic problem for marker-passing techniques. We use a probabilistic analysis to justify a method for quickly identifying and rejecting useless paths. Using the same analysis, we identify key conditions and assumptions necessary for marker-passing to perform well.
A reason maintenance system which extends an ATMS through Mukaidono's fuzzy logic is described. It supports a problem solver in situations affected by incomplete information and vague data, by allowing nonmonotonic inferences and the revision of previous conclusions when contradictions are detected.
This paper outlines a methodology for analyzing the representational support for knowledge-based decision-modeling in a broad domain. A relevant set of inference patterns and knowledge types are identified. By comparing the analysis results to existing representations, some insights are gained into a design approach for integrating categorical and uncertain knowledge in a context sensitive manner.
This paper proposes a new method for solving Bayesian decision problems. The method consists of representing a Bayesian decision problem as a valuation-based system and applying a fusion algorithm for solving it. The fusion algorithm is a hybrid of local computational methods for computation of marginals of joint probability distributions and the local computational methods for discrete optimization problems.
Irrelevance-based partial MAPs are useful constructs for domain-independent explanation using belief networks. We look at two definitions for such partial MAPs, and prove important properties that are useful in designing algorithms for computing them effectively. We make use of these properties in modifying our standard MAP best-first algorithm, so as to handle irrelevance-based partial MAPs.
The relationship between belief networks and relational databases is examined. Based on this analysis, a method to construct belief networks automatically from statistical relational data is proposed. A comparison between our method and other methods shows that our method has several advantages when generalization or prediction is deeded.
A general notion of algebraic conditional plausibility measures is defined. Probability measures, ranking functions, possibility measures, and (under the appropriate definitions) sets of probability measures can all be viewed as defining algebraic conditional plausibility measures. It is shown that the technology of Bayesian networks can be applied to algebraic conditional plausibility measures.
Preferences among acts are analyzed in the style of L. Savage, but as partially ordered. The rationality postulates considered are weaker than Savage's on three counts. The Sure Thing Principle is derived in this setting. The postulates are shown to lead to a characterization of generalized qualitative probability that includes and blends both traditional qualitative probability and the ranked structures used in logical approaches.
This paper studies quantum annealing (QA) for clustering, which can be seen as an extension of simulated annealing (SA). We derive a QA algorithm for clustering and propose an annealing schedule, which is crucial in practice. Experiments show the proposed QA algorithm finds better clustering assignments than SA. Furthermore, QA is as easy as SA to implement.
We show how, and under which conditions, the equilibrium states of a first-order Ordinary Differential Equation (ODE) system can be described with a deterministic Structural Causal Model (SCM). Our exposition sheds more light on the concept of causality as expressed within the framework of Structural Causal Models, especially for cyclic models.
Cox's well-known theorem justifying the use of probability is shown not to hold in finite domains. The counterexample also suggests that Cox's assumptions are insufficient to prove the result even in infinite domains. The same counterexample is used to disprove a result of Fine on comparative conditional probability.
PDDL was originally conceived and constructed as a lingua franca for the International Planning Competition. PDDL2.1 embodies a set of extensions intended to support the expression of something closer to real planning problems. This objective has only been partially achieved, due in large part to a deliberate focus on not moving too far from classical planning models and solution methods.
I comment on the PDDL 2.1 language and its use in the planning competition, focusing on the choices made for accommodating time and concurrency. I also discuss some methodological issues that have to do with the move toward more expressive planning languages and the balance needed in planning research between semantics and computation.
Attribute weighting and differential weighting, two major mechanisms for computing context-dependent similarity or dissimilarity measures are studied and compared. A dissimilarity measure based on subset size in the context is proposed and its metrization and application are given. It is also shown that while all attribute weighting dissimilarity measures are metrics differential weighting dissimilarity measures are usually non-metric.
A similarity network is a tool for constructing belief networks for the diagnosis of a single fault. In this paper, we examine modifications to the similarity-network representation that facilitate the construction of belief networks for the diagnosis of multiple coexisting faults.
Incidence Calculus and Dempster-Shafer Theory of Evidence are both theories to describe agents' degrees of belief in propositions, thus being appropriate to represent uncertainty in reasoning systems. This paper presents a straightforward equivalence proof between some special cases of these theories.
After a brief introduction to causal probabilistic networks and the HUGIN approach, the problem of conflicting data is discussed. A measure of conflict is defined, and it is used in the medical diagnostic system MUNIN. Finally, it is discussed how to distinguish between conflicting data and a rare case.
An efficient algorithm is developed that identifies all independencies implied by the topology of a Bayesian network. Its correctness and maximality stems from the soundness and completeness of d-separation with respect to probability theory. The algorithm runs in time O (l E l) where E is the number of edges in the network.
Measures of uncertainty and divergence are introduced for interval-valued probability distributions and are shown to have desirable mathematical properties. A maximum uncertainty inference procedure for marginal interval distributions is presented. A technique for reconstruction of interval distributions from projections is developed based on this inference procedure
The most difficult task in probabilistic reasoning may be handling directed cycles in belief networks. To the best knowledge of this author, there is no serious discussion of this problem at all in the literature of probabilistic reasoning so far.
We discuss the Dempster-Shafer theory of evidence. We introduce a concept of monotonicity which is related to the diminution of the range between belief and plausibility. We show that the accumulation of knowledge in this framework exhibits a nonmonotonic property. We show how the belief structure can be used to represent typical or commonsense knowledge.
This paper demonstrates a method for using belief-network algorithms to solve influence diagram problems. In particular, both exact and approximation belief-network algorithms may be applied to solve influence-diagram problems. More generally, knowing the relationship between belief-network and influence-diagram problems may be useful in the design and development of more efficient influence diagram algorithms.
This paper advocates the usefulness of new theories of uncertainty for the purpose of modeling some facets of uncertain knowledge, especially vagueness, in AI. It can be viewed as a partial reply to Cheeseman's (among others) defense of probability.
This paper addresses the problem of resolving errors under uncertainty in a rule-based system. A new approach has been developed that reformulates this problem as a neural-network learning problem. The strength and the fundamental limitations of this approach are explored and discussed. The main result is that neural heuristics can be applied to solve some but not all problems in rule-based systems.
This paper addresses a prevailing assumption in single-agent heuristic search theory- that problem-solving algorithms should guarantee shortest-path solutions, which are typically called optimal. Optimality implies a metric for judging solution quality, where the optimal solution is the solution with the highest quality. When path-length is the metric, we will distinguish such solutions as p-optimal.
Uncertainty enters into human reasoning and inference in at least two ways. It is reasonable to suppose that there will be roles for these distinct uses of uncertainty also in automated reasoning.
An approximation method is presented for probabilistic inference with continuous random variables. These problems can arise in many practical problems, in particular where there are "second order" probabilities. The approximation, based on the Gaussian influence diagram, iterates over linear approximations to the inference problem.
In pattern analysis, information regarding an object can often be drawn from its surroundings. This paper presents a method for handling uncertainty when using context of symbols and texts for analyzing technical drawings. The method is based on Dempster-Shafer theory and possibility theory.
The apparent failure of individual probabilistic expressions to distinguish uncertainty about truths from uncertainty about probabilistic assessments have prompted researchers to seek formalisms where the two types of uncertainties are given notational distinction. This paper demonstrates that the desired distinction is already a built-in feature of classical probabilistic models, thus, specialized notations are unnecessary.
This paper discusses an expert system shell that integrates rule-based reasoning and the Dempster-Shafer evidence combination scheme. Domain knowledge is stored as rules with associated belief functions. The reasoning component uses a combination of forward and backward inferencing mechanisms to allow interaction with users in a mixed-initiative format.
An evidential reasoning mechanism based on the Dempster-Shafer theory of evidence is introduced. Its performance in real-world image analysis is compared with other mechanisms based on the Bayesian formalism and a simple weight combination method.
In this paper, we present some results of evidential reasoning in understanding multispectral images of remote sensing systems. The Dempster-Shafer approach of combination of evidences is pursued to yield contextual classification results, which are compared with previous results of the Bayesian context free classification, contextual classifications of dynamic programming and stochastic relaxation approaches.
An automated explanation facility for Bayesian conditioning aimed at improving user acceptance of probability-based decision support systems has been developed. The domain-independent facility is based on an information processing perspective on reasoning about conditional evidence that accounts both for biased and normative inferences. Experimental results indicate that the facility is both acceptable to naive users and effective in improving understanding.
The generalized fault diagram, a data structure for failure analysis based on the influence diagram, is defined. Unlike the fault tree, this structure allows for dependence among the basic events and replicated logical elements. A heuristic procedure is developed for efficient processing of these structures.
A learning algorithm is presented which given the structure of a causal tree, will estimate its link probabilities by sequential measurements on the leaves only. Internal nodes of the tree represent conceptual (hidden) variables inaccessible to observation. The method described is incremental, local, efficient, and remains robust to measurement imprecisions.
Linear representations for a subclass of boolean symmetric functions selected by a parity condition are shown to constitute a generalization of the linear constraints on probabilities introduced by Boole. These linear constraints are necessary to compute probabilities of events with relations between the. arbitrarily specified with propositional calculus boolean formulas.
Bayesian networks provide a probabilistic semantics for qualitative assertions about likelihood. A qualitative reasoner based on an algebra over these assertions can derive further conclusions about the influence of actions. While the conclusions are much weaker than those computed from complete probability distributions, they are still valuable for suggesting potential actions, eliminating obviously inferior plans, identifying important tradeoffs, and explaining probabilistic models.
In many cases commonsense knowledge consists of knowledge of what is usual. In this paper we develop a system for reasoning with usual information. This system is based upon the fact that these pieces of commonsense information involve both a probabilistic aspect and a granular aspect. We implement this system with the aid of possibility-probability granules.
In the current versions of the Dempster-Shafer theory, the only essential restriction on the validity of the rule of combination is that the sources of evidence must be statistically independent. Under this assumption, it is permissible to apply the Dempster-Shafer rule to two or mere distinct probability distributions.
The paper demonstrates that strict adherence to probability theory does not preclude the use of concurrent, self-activated constraint-propagation mechanisms for managing uncertainty. Maintaining local records of sources-of-belief allows both predictive and diagnostic inferences to be activated simultaneously and propagate harmoniously towards a stable equilibrium.
General problems in analyzing information in a probabilistic database are considered. The practical difficulties (and occasional advantages) of storing uncertain data, of using it conventional forward- or backward-chaining inference engines, and of working with a probabilistic version of resolution are discussed. The background for this paper is the incorporation of uncertain reasoning facilities in MRS, a general-purpose expert system building tool.
Acyclic directed mixed graphs, also known as semi-Markov models represent the conditional independence structure induced on an observed margin by a DAG model with latent variables. In this paper we present a factorization criterion for these models that is equivalent to the global Markov property given by (the natural extension of) d-separation.
Non-obviousness or inventive step is a general requirement for patentability in most patent law systems. An invention should be at an adequate distance beyond its prior art in order to be patented. This short paper provides an overview on a methodology proposed for legal norm validation of FSTP facts using rule reasoning approach.
We present a method to prove the decidability of provability in several well-known inference systems. This method generalizes both cut-elimination and the construction of an automaton recognizing the provable propositions.
Quantum decision systems are being increasingly considered for use in artificial intelligence applications. Classical and quantum nodes can be distinguished based on certain correlations in their states. This paper investigates some properties of the states obtained in a decision tree structure. How these correlations may be mapped to the decision tree is considered. Classical tree representations and approximations to quantum states are provided.
Current measures of machine intelligence are either difficult to evaluate or lack the ability to test a robot's problem-solving capacity in open worlds. We propose a novel evaluation framework based on the formal notion of MacGyver Test which provides a practical way for assessing the resilience and resourcefulness of artificial agents.
We propose the creation of a systematic effort to identify and replicate key findings in neuroscience and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of artificial intelligence has been sufficiently validated to play a role in the design of AI systems.
Research on integrated neural-symbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to strive for applicable implementations and use cases. Recent work has covered a great variety of logics used in artificial intelligence and provides a multitude of techniques for dealing with them within the context of artificial neural networks. We present a comprehensive survey of the field of neural-symbolic integration, including a new classification of system according to their architectures and abilities.
The technological singularity refers to a hypothetical scenario in which technological advances virtually explode. The most popular scenario is the creation of super-intelligent algorithms that recursively create ever higher intelligences. It took many decades for these ideas to spread from science fiction to popular science magazines and finally to attract the attention of serious philosophers. David Chalmers' (JCS 2010) article is the first comprehensive philosophical analysis of the singularity in a respected philosophy journal. The motivation of my article is to augment Chalmers' and to discuss some issues not addressed by him, in particular what it could mean for intelligence to explode. In this course, I will (have to) provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity.
This paper presents a non-manual design engineering method based on heuristic search algorithm to search for candidate agents in the solution space which formed by artificial intelligence agents modeled on the base of bionics.Compared with the artificial design method represented by meta-learning and the bionics method represented by the neural architecture chip,this method is more feasible for realizing artificial general intelligence,and it has a much better interaction with cognitive neuroscience;at the same time,the engineering method is based on the theoretical hypothesis that the final learning algorithm is stable in certain scenarios,and has generalization ability in various scenarios.The paper discusses the theory preliminarily and proposes the possible correlation between the theory and the fixed-point theorem in the field of mathematics.Limited by the author's knowledge level,this correlation is proposed only as a kind of conjecture.
Decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameterless theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI model is the most intelligent unbiased agent possible. We outline for a number of problem classes, including sequence prediction, strategic games, function minimization, reinforcement and supervised learning, how the AIXI model can formally solve them. The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXI-tl, which is still effectively more intelligent than any other time t and space l bounded agent. The computation time of AIXI-tl is of the order tx2^l. Other discussed topics are formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches.
Computer-supported learning is an increasingly important form of study since it allows for independent learning and individualized instruction. In this paper, we discuss a novel approach to developing an intelligent tutoring system for teaching textbook-style mathematical proofs. We characterize the particularities of the domain and discuss common ITS design models. Our approach is motivated by phenomena found in a corpus of tutorial dialogs that were collected in a Wizard-of-Oz experiment. We show how an intelligent tutor for textbook-style mathematical proofs can be built on top of an adapted assertion-level proof assistant by reusing representations and proof search strategies originally developed for automated and interactive theorem proving. The resulting prototype was successfully evaluated on a corpus of tutorial dialogs and yields good results.
The main prospective aim of modern research related to Artificial Intelligence is the creation of technical systems that implement the idea of Strong Intelligence. According our point of view the path to the development of such systems comes through the research in the field related to perceptions. Here we formulate the model of the perception of external world which may be used for the description of perceptual activity of intelligent beings. We consider a number of issues related to the development of the set of patterns which will be used by the intelligent system when interacting with environment. The key idea of the presented perception model is the idea of subjective reality. The principle of the relativity of perceived world is formulated. It is shown that this principle is the immediate consequence of the idea of subjective reality. In this paper we show how the methodology of subjective reality may be used for the creation of different types of Strong AI systems.
It has been commonly argued, on the basis of Goedel's theorem and related mathematical results, that true artificial intelligence cannot exist. Penrose has further deduced from the existence of human intelligence that fundamental changes in physical theories are needed. I provide an elementary demonstration that these deductions are mistaken.
The theory of computational complexity is used to underpin a recent model of neocortical sensory processing. We argue that encoding into reconstruction networks is appealing for communicating agents using Hebbian learning and working on hard combinatorial problems, which are easy to verify. Computational definition of the concept of intelligence is provided. Simulations illustrate the idea.
This paper presents an intelligent tutoring system, GeoTutor, for Euclidean Geometry that is automatically able to synthesize proof problems and their respective solutions given a geometric figure together with a set of properties true of it. GeoTutor can provide personalized practice problems that address student deficiencies in the subject matter.
In this paper, we will expound upon the concepts proffered in [1], where we proposed an information theoretic approach to intelligence in the computational sense. We will examine data and meme aggregation, and study the effect of limited resources on the resulting meme amplitudes.
IUIs aim to incorporate intelligent automated capabilities in human computer interaction, where the net impact is a human-computer interaction that improves performance or usability in critical ways. It also involves designing and implementing an artificial intelligence (AI) component that effectively leverages human skills and capabilities, so that human performance with an application excels. IUIs embody capabilities that have traditionally been associated more strongly with humans than with computers: how to perceive, interpret, learn, use language, reason, plan, and decide.
The concept of "task" is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical foundations allow thorough evaluation of designs by methodical manipulation of well understood parameters with a known role and importance; this allows an aeronautics engineer, for instance, to systematically assess the effects of wind speed on an airplane's performance and stability. No framework exists in AI that allows this kind of methodical manipulation: Performance results on the few tasks in current use (cf. board games, question-answering) cannot be easily compared, however similar or different. The issue is even more acute with respect to artificial *general* intelligence systems, which must handle unanticipated tasks whose specifics cannot be known beforehand. A *task theory* would enable addressing tasks at the *class* level, bypassing their specifics, providing the appropriate formalization and classification of tasks, environments, and their parameters, resulting in more rigorous ways of measuring, comparing, and evaluating intelligent behavior. Even modest improvements in this direction would surpass the current ad-hoc nature of machine learning and AI evaluation. Here we discuss the main elements of the argument for a task theory and present an outline of what it might look like for physical tasks.
This is the second part of a paper on Conscious Intelligent Systems. We use the understanding gained in the first part (Conscious Intelligent Systems Part 1: IXI (arxiv id cs.AI/0612056)) to look at understanding. We see how the presence of mind affects understanding and intelligent systems; we see that the presence of mind necessitates language. The rise of language in turn has important effects on understanding. We discuss the humanoid question and how the question of self-consciousness (and by association mind/thought/language) would affect humanoids too.
We propose that operator induction serves as an adequate model of perception. We explain how to reduce universal agent models to operator induction. We propose a universal measure of operator induction fitness, and show how it can be used in a reinforcement learning model and a homeostasis (self-preserving) agent based on the free energy principle. We show that the action of the homeostasis agent can be explained by the operator induction model.
Computational Intelligence (CI) is a sub-branch of Artificial Intelligence paradigm focusing on the study of adaptive mechanisms to enable or facilitate intelligent behavior in complex and changing environments. There are several paradigms of CI [like artificial neural networks, evolutionary computations, swarm intelligence, artificial immune systems, fuzzy systems and many others], each of these has its origins in biological systems [biological neural systems, natural Darwinian evolution, social behavior, immune system, interactions of organisms with their environment]. Most of those paradigms evolved into separate machine learning (ML) techniques, where probabilistic methods are used complementary with CI techniques in order to effectively combine elements of learning, adaptation, evolution and Fuzzy logic to create heuristic algorithms that are, in some sense, intelligent. The current trend is to develop consensus techniques, since no single machine learning algorithms is superior to others in all possible situations. In order to overcome this problem several meta-approaches were proposed in ML focusing on the integration of results from different methods into single prediction. We discuss here the Landau theory for the nonlinear equation that can describe the adaptive integration of information acquired from an ensemble of independent learning agents. The influence of each individual agent on other learners is described similarly to the social impact theory. The final decision outcome for the consensus system is calculated using majority rule in the stationary limit, yet the minority solutions can survive inside the majority population as the complex intermittent clusters of opposite opinion.
This paper describes a novel method for building affectively intelligent human-interactive agents. The method is based on a key sociological insight that has been developed and extensively verified over the last twenty years, but has yet to make an impact in artificial intelligence. The insight is that resource bounded humans will, by default, act to maintain affective consistency. Humans have culturally shared fundamental affective sentiments about identities, behaviours, and objects, and they act so that the transient affective sentiments created during interactions confirm the fundamental sentiments. Humans seek and create situations that confirm or are consistent with, and avoid and supress situations that disconfirm or are inconsistent with, their culturally shared affective sentiments. This "affect control principle" has been shown to be a powerful predictor of human behaviour. In this paper, we present a probabilistic and decision-theoretic generalisation of this principle, and we demonstrate how it can be leveraged to build affectively intelligent artificial agents. The new model, called BayesAct, can maintain multiple hypotheses about sentiments simultaneously as a probability distribution, and can make use of an explicit utility function to make value-directed action choices. This allows the model to generate affectively intelligent interactions with people by learning about their identity, predicting their behaviours using the affect control principle, and taking actions that are simultaneously goal-directed and affect-sensitive. We demonstrate this generalisation with a set of simulations. We then show how our model can be used as an emotional "plug-in" for artificially intelligent systems that interact with humans in two different settings: an exam practice assistant (tutor) and an assistive device for persons with a cognitive disability.
Web intelligence can be considered as a subset of Artificial Intelligence. It uses existing data in web to produce new data, knowledge and wisdom to support decision making and new predictions for web users. Artificial Intelligence is ever changing and evolving field of computer science and it is extensively used in wide array of web based business applications. Although it is used substantially in web based systems in developed countries, it is not examined whether it is being substantially used in Sri Lanka. Every Sri Lankan citizen depends on Public Service more or less throughout his/ her life time and at least more than 3 times: at birth, marriage and death. So providing most of these services to its citizen, Sri Lankan Government uses more or less of its country web portal. This paper presents a model to evaluate web intelligence capability based on weight to key functionalities with respect to web intelligence. The government websites were checked by the proposed criteria to show the potential of using web intelligent technology to provide website based services. The result indicates that the use of web intelligence techniques openly and publicly to provide web based services through government web portal to its citizens is not satisfactory. It also indicates that lack of using the technologies pertaining to web intelligence in the public service web hinders the most of the advantages that citizen and government can gain from such technological involvement.
The recognition of optical characters is known to be one of the earliest applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In this paper, a simplified neural approach to recognition of optical or visual characters is portrayed and discussed. The document is expected to serve as a resource for learners and amateur investigators in pattern recognition, neural networking and related disciplines.
Memory refinements are designed below to detect those sequences of actions that have been repeated a given number n. Subsequently such sequences are permitted to run without CPU involvement. This mimics human learning. Actions are rehearsed and once learned, they are performed automatically without conscious involvement.
The study of belief change has been an active area in philosophy and AI. In recent years two special cases of belief change, belief revision and belief update, have been studied in detail. In a companion paper (Friedman & Halpern, 1997), we introduce a new framework to model belief change. This framework combines temporal and epistemic modalities with a notion of plausibility, allowing us to examine the change of beliefs over time. In this paper, we show how belief revision and belief update can be captured in our framework. This allows us to compare the assumptions made by each method, and to better understand the principles underlying them. In particular, it shows that Katsuno and Mendelzon's notion of belief update (Katsuno & Mendelzon, 1991a) depends on several strong assumptions that may limit its applicability in artificial intelligence. Finally, our analysis allow us to identify a notion of minimal change that underlies a broad range of belief change operations including revision and update.
It is shown that Darwiche and Pearl's postulates imply an interesting property, not noticed by the authors.
The following four classes of computational problems are equivalent: solving matrix games, solving linear programs, best $l^{\infty}$ linear approximation, best $l^1$ linear approximation.
Open Source Software (OSS) often relies on large repositories, like SourceForge, for initial incubation. The OSS repositories offer a large variety of meta-data providing interesting information about projects and their success. In this paper we propose a data mining approach for training classifiers on the OSS meta-data provided by such data repositories. The classifiers learn to predict the successful continuation of an OSS project. The `successfulness' of projects is defined in terms of the classifier confidence with which it predicts that they could be ported in popular OSS projects (such as FreeBSD, Gentoo Portage).
The report gives an overview about activities on the topic Semantic Web. It has been released as technical report for the project "KTweb -- Connecting Knowledge Technologies Communities" in 2003.
This manuscripts contains the proofs for "A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction".
Product take-back legislation forces manufacturers to bear the costs of collection and disposal of products that have reached the end of their useful lives. In order to reduce these costs, manufacturers can consider reuse, remanufacturing and/or recycling of components as an alternative to disposal. The implementation of such alternatives usually requires an appropriate reverse supply chain management. With the concepts of reverse supply chain are gaining popularity in practice, the use of artificial intelligence approaches in these areas is also becoming popular. As a result, the purpose of this paper is to give an overview of the recent publications concerning the application of artificial intelligence techniques to reverse supply chain with emphasis on certain types of product returns.
Nowadays, the huge amount of information distributed through the Web motivates studying techniques to be adopted in order to extract relevant data in an efficient and reliable way. Both academia and enterprises developed several approaches of Web data extraction, for example using techniques of artificial intelligence or machine learning. Some commonly adopted procedures, namely wrappers, ensure a high degree of precision of information extracted from Web pages, and, at the same time, have to prove robustness in order not to compromise quality and reliability of data themselves. In this paper we focus on some experimental aspects related to the robustness of the data extraction process and the possibility of automatically adapting wrappers. We discuss the implementation of algorithms for finding similarities between two different version of a Web page, in order to handle modifications, avoiding the failure of data extraction tasks and ensuring reliability of information extracted. Our purpose is to evaluate performances, advantages and draw-backs of our novel system of automatic wrapper adaptation.
Our hypothesis is that by equipping certain agents in a multi-agent system controlling an intelligent building with automated decision support, two important factors will be increased. The first is energy saving in the building. The second is customer value---how the people in the building experience the effects of the actions of the agents. We give evidence for the truth of this hypothesis through experimental findings related to tools for artificial decision making. A number of assumptions related to agent control, through monitoring and delegation of tasks to other kinds of agents, of rooms at a test site are relaxed. Each assumption controls at least one uncertainty that complicates considerably the procedures for selecting actions part of each such agent. We show that in realistic decision situations, room-controlling agents can make bounded rational decisions even under dynamic real-time constraints. This result can be, and has been, generalized to other domains with even harsher time constraints.
The chinese room problem asks if computers can think; I ask here if most humans can.
Machines are possible to have some artificial intelligence like human beings owing to particular algorithms or software. Such machines could learn knowledge from what people taught them and do works according to the knowledge. In practical learning cases, the data is often extremely complicated and large, thus classical learning machines often need huge computational resources. Quantum machine learning algorithm, on the other hand, could be exponentially faster than classical machines using quantum parallelism. Here, we demonstrate a quantum machine learning algorithm on a four-qubit NMR test bench to solve an optical character recognition problem, also known as the handwriting recognition. The quantum machine learns standard character fonts and then recognize handwritten characters from a set with two candidates. To our best knowledge, this is the first artificial intelligence realized on a quantum processor. Due to the widespreading importance of artificial intelligence and its tremendous consuming of computational resources, quantum speedup would be extremely attractive against the challenges from the Big Data.
Outline of several strategies for using Gaussian processes as surrogate models for the covariance matrix adaptation evolution strategy (CMA-ES).
We propose a funny representation of SAT. While the primary interest is to present propositional satisfiability in a playful way for pedagogical purposes, it could also inspire new search heuristics.
This essay explores the limits of Turing machines concerning the modeling of minds and suggests alternatives to go beyond those limits.
The question how an agent is affected by its embodiment has attracted growing attention in recent years. A new field of artificial intelligence has emerged, which is based on the idea that intelligence cannot be understood without taking into account embodiment. We believe that a formal approach to quantifying the embodiment's effect on the agent's behaviour is beneficial to the fields of artificial life and artificial intelligence. The contribution of an agent's body and environment to its behaviour is also known as morphological computation. Therefore, in this work, we propose a quantification of morphological computation, which is based on an information decomposition of the sensorimotor loop into shared, unique and synergistic information. In numerical simulation based on a formal representation of the sensorimotor loop, we show that the unique information of the body and environment is a good measure for morphological computation. The results are compared to our previously derived quantification of morphological computation.
Massive Open Online Courses (MOOCs) have gained tremendous popularity in the last few years. Thanks to MOOCs, millions of learners from all over the world have taken thousands of high-quality courses for free. Putting together an excellent MOOC ecosystem is a multidisciplinary endeavour that requires contributions from many different fields. Artificial intelligence (AI) and data mining (DM) are two such fields that have played a significant role in making MOOCs what they are today. By exploiting the vast amount of data generated by learners engaging in MOOCs, DM improves our understanding of the MOOC ecosystem and enables MOOC practitioners to deliver better courses. Similarly, AI, supported by DM, can greatly improve student experience and learning outcomes. In this survey paper, we first review the state-of-the-art artificial intelligence and data mining research applied to MOOCs, emphasising the use of AI and DM tools and techniques to improve student engagement, learning outcomes, and our understanding of the MOOC ecosystem. We then offer an overview of key trends and important research to carry out in the fields of AI and DM so that MOOCs can reach their full potential.
Cybersecurity research involves publishing papers about malicious exploits as much as publishing information on how to design tools to protect cyber-infrastructure. It is this information exchange between ethical hackers and security experts, which results in a well-balanced cyber-ecosystem. In the blooming domain of AI Safety Engineering, hundreds of papers have been published on different proposals geared at the creation of a safe machine, yet nothing, to our knowledge, has been published on how to design a malevolent machine. Availability of such information would be of great value particularly to computer scientists, mathematicians, and others who have an interest in AI safety, and who are attempting to avoid the spontaneous emergence or the deliberate creation of a dangerous AI, which can negatively affect human activities and in the worst case cause the complete obliteration of the human species. This paper provides some general guidelines for the creation of a Malevolent Artificial Intelligence (MAI).
We use the theory of defaults and their meaning of [GS16] to develop (the outline of a) new theory of argumentation.
Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker is the quintessential game of imperfect information, and a longstanding challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning. In a study involving 44,000 hands of poker, DeepStack defeated with statistical significance professional poker players in heads-up no-limit Texas hold'em. The approach is theoretically sound and is shown to produce more difficult to exploit strategies than prior approaches.
In this article, we introduce a new conception of a family of esport games called Samu Entropy to try to improve dataflow program graphs like the ones that are based on Google's TensorFlow. Currently, the Samu Entropy project specifies only requirements for new esport games to be developed with particular attention to the investigation of the relationship between esport and artificial intelligence. It is quite obvious that there is a very close and natural relationship between esport games and artificial intelligence. Furthermore, the project Samu Entropy focuses not only on using artificial intelligence, but on creating AI in a new way. We present a reference game called Face Battle that implements the Samu Entropy requirements.
With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of their nested non-linear structure, these highly successful machine learning and artificial intelligence models are usually applied in a black box manner, i.e., no information is provided about what exactly makes them arrive at their predictions. Since this lack of transparency can be a major drawback, e.g., in medical applications, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This paper summarizes recent developments in this field and makes a plea for more interpretability in artificial intelligence. Furthermore, it presents two approaches to explaining predictions of deep learning models, one method which computes the sensitivity of the prediction with respect to changes in the input and one approach which meaningfully decomposes the decision in terms of the input variables. These methods are evaluated on three classification tasks.
Artificial Intelligence is a central topic in the computer science curriculum. From the year 2011 a project-based learning methodology based on computer games has been designed and implemented into the intelligence artificial course at the University of the Bio-Bio. The project aims to develop software-controlled agents (bots) which are programmed by using heuristic algorithms seen during the course. This methodology allows us to obtain good learning results, however several challenges have been founded during its implementation.   In this paper we show how linguistic descriptions of data can help to provide students and teachers with technical and personalized feedback about the learned algorithms. Algorithm behavior profile and a new Turing test for computer games bots based on linguistic modelling of complex phenomena are also proposed in order to deal with such challenges.   In order to show and explore the possibilities of this new technology, a web platform has been designed and implemented by one of authors and its incorporation in the process of assessment allows us to improve the teaching learning process.
The concept of innateness is rarely discussed in the context of artificial intelligence. When it is discussed, or hinted at, it is often the context of trying to reduce the amount of innate machinery in a given system. In this paper, I consider as a test case a recent series of papers by Silver et al (Silver et al., 2017a) on AlphaGo and its successors that have been presented as an argument that a "even in the most challenging of domains: it is possible to train to superhuman level, without human examples or guidance", "starting tabula rasa."   I argue that these claims are overstated, for multiple reasons. I close by arguing that artificial intelligence needs greater attention to innateness, and I point to some proposals about what that innateness might look like.
It is undeniable that artificial intelligence (AI) and blockchain concepts are spreading at a phenomenal rate. Both technologies have distinct degree of technological complexity and multi-dimensional business implications. However, a common misunderstanding about blockchain concept, in particular, is that blockchain is decentralized and is not controlled by anyone. But the underlying development of a blockchain system is still attributed to a cluster of core developers. Take smart contract as an example, it is essentially a collection of codes (or functions) and data (or states) that are programmed and deployed on a blockchain (say, Ethereum) by different human programmers. It is thus, unfortunately, less likely to be free of loopholes and flaws. In this article, through a brief overview about how artificial intelligence could be used to deliver bug-free smart contract so as to achieve the goal of blockchain 2.0, we to emphasize that the blockchain implementation can be assisted or enhanced via various AI techniques. The alliance of AI and blockchain is expected to create numerous possibilities.
The use of artificial intelligence intelligencein medicine can be traced back to 1968 when Paycha published his paper Le diagnostic a l'aide d'intelligences artificielle, presentation de la premiere machine diagnostri. Few years later Shortliffe et al. presented an expert system named Mycin which was able to identify bacteria causing severe blood infections and to recommend antibiotics. Despite the fact that Mycin outperformed members of the Stanford medical school in the reliability of diagnosis it was never used in practice due to a legal issue who do you sue if it gives a wrong diagnosis?. However only in 2016 when the artificial intelligence software built into the IBM Watson AI platform correctly diagnosed and proposed an effective treatment for a 60-year-old womans rare form of leukemia the AI use in medicine become really popular.On of first papers presenting the use of AI in paediatrics was published in 1984. The paper introduced a computer-assisted medical decision making system called SHELP.
The AGINAO is a project to create a human-level artificial general intelligence system (HL AGI) embodied in the Aldebaran Robotics' NAO humanoid robot. The dynamical and open-ended cognitive engine of the robot is represented by an embedded and multi-threaded control program, that is self-crafted rather than hand-crafted, and is executed on a simulated Universal Turing Machine (UTM). The actual structure of the cognitive engine emerges as a result of placing the robot in a natural preschool-like environment and running a core start-up system that executes self-programming of the cognitive layer on top of the core layer. The data from the robot's sensory devices supplies the training samples for the machine learning methods, while the commands sent to actuators enable testing hypotheses and getting a feedback. The individual self-created subroutines are supposed to reflect the patterns and concepts of the real world, while the overall program structure reflects the spatial and temporal hierarchy of the world dependencies. This paper focuses on the details of the self-programming approach, limiting the discussion of the applied cognitive architecture to a necessary minimum.
This text introduces the twin deadlocks of strong artificial life. Conceptualization of life is a deadlock both because of the existence of a continuum between the inert and the living, and because we only know one instance of life. Computationalism is a second deadlock since it remains a matter of faith. Nevertheless, artificial life realizations quickly progress and recent constructions embed an always growing set of the intuitive properties of life. This growing gap between theory and realizations should sooner or later crystallize in some kind of paradigm shift and then give clues to break the twin deadlocks.
Artificial Chemistries (ACs) are symbolic chemical metaphors for the exploration of Artificial Life, with specific focus on the problem of biogenesis or the origin of life. This paper presents authors thoughts towards defining a unified framework to characterize and classify symbolic artificial chemistries by devising appropriate formalism to capture semantic and organizational information. We identify three basic high level abstractions in initial proposal for this framework viz., information, computation, and communication. We present an analysis of two important notions of information, namely, Shannon's Entropy and Algorithmic Information, and discuss inductive and deductive approaches for defining the framework.
Innate immunity now occupies a central role in immunology. However, artificial immune system models have largely been inspired by adaptive not innate immunity. This paper reviews the biological principles and properties of innate immunity and, adopting a conceptual framework, asks how these can be incorporated into artificial models. The aim is to outline a meta-framework for models of innate immunity.
We present chemlambda (or the chemical concrete machine), an artificial chemistry with the following properties: (a) is Turing complete, (b) has a model of decentralized, distributed computing associated to it, (c) works at the level of individual (artificial) molecules, subject of reversible, but otherwise deterministic interactions with a small number of enzymes, (d) encodes information in the geometrical structure of the molecules and not in their numbers, (e) all interactions are purely local in space and time. This is part of a larger project to create computing, artificial chemistry and artificial life in a distributed context, using topological and graphical languages.
If you are an artificial intelligence researcher, you should look to video games as ideal testbeds for the work you do. If you are a video game developer, you should look to AI for the technology that makes completely new types of games possible. This chapter lays out the case for both of these propositions. It asks the question "what can video games do for AI", and discusses how in particular general video game playing is the ideal testbed for artificial general intelligence research. It then asks the question "what can AI do for video games", and lays out a vision for what video games might look like if we had significantly more advanced AI at our disposal. The chapter is based on my keynote at IJCCI 2015, and is written in an attempt to be accessible to a broad audience.
The objective of this paper is to introduce an artificial intelligence based optimization approach, which is inspired from Piagets theory on cognitive development. The approach has been designed according to essential processes that an individual may experience while learning something new or improving his / her knowledge. These processes are associated with the Piagets ideas on an individuals cognitive development. The approach expressed in this paper is a simple algorithm employing swarm intelligence oriented tasks in order to overcome single-objective optimization problems. For evaluating effectiveness of this early version of the algorithm, test operations have been done via some benchmark functions. The obtained results show that the approach / algorithm can be an alternative to the literature in terms of single-objective optimization. The authors have suggested the name: Cognitive Development Optimization Algorithm (CoDOA) for the related intelligent optimization approach.
A recent issue of a popular computing journal asked which laws would apply if a self-driving car killed a pedestrian. This paper considers the question of legal liability for artificially intelligent computer systems. It discusses whether criminal liability could ever apply; to whom it might apply; and, under civil law, whether an AI program is a product that is subject to product design legislation or a service to which the tort of negligence applies. The issue of sales warranties is also considered. A discussion of some of the practical limitations that AI systems are subject to is also included.
Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of machine learning and neural networks, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning are in many ways interdependent. This paper discusses the nature of some of these interdependencies and proposes a general framework called FLARE, that combines inductive learning using prior knowledge together with reasoning in a propositional setting. Several examples that test the framework are presented, including classical induction, many important reasoning protocols and two simple expert systems.
Inspired by Hofstadter's Coffee-House Conversation (1982) and by the science fiction short story SAM by Schattschneider (1988), we propose and discuss criteria for non-mechanical intelligence. Firstly, we emphasize the practical need for such tests in view of massively multiuser online role-playing games (MMORPGs) and virtual reality systems like Second Life. Secondly, we demonstrate Second Life as a useful framework for implementing (some iterations of) that test.
Autonomous intelligent agent research is a domain situated at the forefront of artificial intelligence. Interest-based negotiation (IBN) is a form of negotiation in which agents exchange information about their underlying goals, with a view to improve the likelihood and quality of a offer. In this paper we model and verify a multi-agent argumentation scenario of resource sharing mechanism to enable resource sharing in a distributed system. We use IBN in our model wherein agents express their interests to the others in the society to gain certain resources.
Most successful Bayesian network (BN) applications to datehave been built through knowledge elicitation from experts.This is difficult and time consuming, which has lead to recentinterest in automated methods for learning BNs from data. We present a case study in the construction of a BN in anintelligent tutoring application, specifically decimal misconceptions. Wedescribe the BN construction using expert elicitation and then investigate how certainexisting automated knowledge discovery methods might support the BN knowledge engineering process.
We propose a formal framework for intelligent systems which can reason about scientific domains, in particular about the carcinogenicity of chemicals, and we study its properties. Our framework is grounded in a philosophy of scientific enquiry and discourse, and uses a model of dialectical argumentation. The formalism enables representation of scientific uncertainty and conflict in a manner suitable for qualitative reasoning about the domain.
This paper describes a domain-specific knowledge acquisition tool for intelligent automated troubleshooters based on Bayesian networks. No Bayesian network knowledge is required to use the tool, and troubleshooting information can be specified as natural and intuitive as possible. Probabilities can be specified in the direction that is most natural to the domain expert. Thus, the knowledge acquisition efficiently removes the traditional knowledge acquisition bottleneck of Bayesian networks.
Like any large system development effort, the construction of a complex belief network model requires systems engineering to manage the design and construction process. We propose a rapid prototyping approach to network engineering. We describe criteria for identifying network modules and the use of "stubs" to represent not-yet-constructed modules. We propose an object oriented representation for belief networks which captures the semantics of the problem in addition to conditional independencies and probabilities. Methods for evaluating complex belief network models are discussed. The ideas are illustrated with examples from a large belief network construction problem in the military intelligence domain.
This note is concerned with a formal analysis of the problem of non-monotonic reasoning in intelligent systems, especially when the uncertainty is taken into account in a quantitative way. A firm connection between logic and probability is established by introducing conditioning notions by means of formal structures that do not rely on quantitative measures. The associated conditional logic, compatible with conditional probability evaluations, is non-monotonic relative to additional evidence. Computational aspects of conditional probability logic are mentioned. The importance of this development lies on its role to provide a conceptual basis for various forms of evidence combination and on its significance to unify multi-valued and non-monotonic logics
This is a preliminary version of visual interpretation integrating multiple sensors in SUCCESSOR, an intelligent, model-based vision system. We pursue a thorough integration of hierarchical Bayesian inference with comprehensive physical representation of objects and their relations in a system for reasoning with geometry, surface materials and sensor models in machine vision. Bayesian inference provides a framework for accruing_ probabilities to rank order hypotheses.
Current approaches to expert systems' reasoning under uncertainty fail to capture the iterative revision process characteristic of intelligent human reasoning. This paper reports on a system, called the Non-monotonic Probabilist, or NMP (Cohen, et al., 1985). When its inferences result in substantial conflict, NMP examines and revises the assumptions underlying the inferences until conflict is reduced to acceptable levels. NMP has been implemented in a demonstration computer-based system, described below, which supports threat correlation and in-flight route replanning by Air Force pilots.
Does the energy requirements for the human brain give energy constraints that give reason to doubt the feasibility of artificial intelligence? This report will review some relevant estimates of brain bioenergetics and analyze some of the methods of estimating brain emulation energy requirements. Turning to AI, there are reasons to believe the energy requirements for de novo AI to have little correlation with brain (emulation) energy requirements since cost could depend merely of the cost of processing higher-level representations rather than billions of neural firings. Unless one thinks the human way of thinking is the most optimal or most easily implementable way of achieving software intelligence, we should expect de novo AI to make use of different, potentially very compressed and fast, processes.
In this paper artificial neural networks and support vector machines are used to reduce the amount of vibration data that is required to estimate the Time Domain Average of a gear vibration signal. Two models for estimating the time domain average of a gear vibration signal are proposed. The models are tested on data from an accelerated gear life test rig. Experimental results indicate that the required data for calculating the Time Domain Average of a gear vibration signal can be reduced by up to 75% when the proposed models are implemented.
In this paper, we present a heuristic operator which aims at simultaneously optimizing the orientations of all the edges in an intermediate Bayesian network structure during the search process. This is done by alternating between the space of directed acyclic graphs (DAGs) and the space of skeletons. The found orientations of the edges are based on a scoring function rather than on induced conditional independences. This operator can be used as an extension to commonly employed search strategies. It is evaluated in experiments with artificial and real-world data.
The study of arguments as abstract entities and their interaction as introduced by Dung (Artificial Intelligence 177, 1995) has become one of the most active research branches within Artificial Intelligence and Reasoning. A main issue for abstract argumentation systems is the selection of acceptable sets of arguments. Value-based argumentation, as introduced by Bench-Capon (J. Logic Comput. 13, 2003), extends Dung's framework. It takes into account the relative strength of arguments with respect to some ranking representing an audience: an argument is subjectively accepted if it is accepted with respect to some audience, it is objectively accepted if it is accepted with respect to all audiences. Deciding whether an argument is subjectively or objectively accepted, respectively, are computationally intractable problems. In fact, the problems remain intractable under structural restrictions that render the main computational problems for non-value-based argumentation systems tractable. In this paper we identify nontrivial classes of value-based argumentation systems for which the acceptance problems are polynomial-time tractable. The classes are defined by means of structural restrictions in terms of the underlying graphical structure of the value-based system. Furthermore we show that the acceptance problems are intractable for two classes of value-based systems that where conjectured to be tractable by Dunne (Artificial Intelligence 171, 2007).
The main topic discussed in this paper is how to use intelligence for biometric decision defuzzification. A neural training model is proposed and tested here as a possible solution for dealing with natural fuzzification that appears between the intra- and inter-class distribution of scores computed during iris recognition tests. It is shown here that the use of proposed neural network support leads to an improvement in the artificial perception of the separation between the intra- and inter-class score distributions by moving them away from each other.
This article provides a brief introduction to the "Theory of Intelligence" and its realisation in the "SP Computer Model". The overall goal of the SP programme of research, in accordance with long-established principles in science, has been the simplification and integration of observations and concepts across artificial intelligence, mainstream computing, mathematics, and human learning, perception, and cognition. In broad terms, the SP system is a brain-like system that takes in "New" information through its senses and stores some or all of it as "Old" information. A central idea in the system is the powerful concept of "SP-multiple-alignment", borrowed and adapted from bioinformatics. This the key to the system's versatility in aspects of intelligence, in the representation of diverse kinds of knowledge, and in the seamless integration of diverse aspects of intelligence and diverse kinds of knowledge, in any combination. There are many potential benefits and applications of the SP system. It is envisaged that the system will be developed as the "SP Machine", which will initially be a software virtual machine, hosted on a high-performance computer, a vehicle for further research and a step towards the development of an industrial-strength SP Machine.
In this paper we demonstrate that it is possible to manage intelligence in constant time as a pre-process to information fusion through a series of processes dealing with issues such as clustering reports, ranking reports with respect to importance, extraction of prototypes from clusters and immediate classification of newly arriving intelligence reports. These methods are used when intelligence reports arrive which concerns different events which should be handled independently, when it is not known a priori to which event each intelligence report is related. We use clustering that runs as a back-end process to partition the intelligence into subsets representing the events, and in parallel, a fast classification that runs as a front-end process in order to put the newly arriving intelligence into its correct information fusion process.
We present an alternative methodology for the analysis of algorithms, based on the concept of expected discounted reward. This methodology naturally handles algorithms that do not always terminate, so it can (theoretically) be used with partial algorithms for undecidable problems, such as those found in artificial general intelligence (AGI) and automated theorem proving. We mention an approach to self-improving AGI enabled by this methodology.   Aug 2017 addendum: This article was originally written with multiple audiences in mind. It is really best put in the following terms. Goertzel, Hutter, Legg, and others have developed a definition of an intelligence score for a general abstract agent: expected lifetime reward in a random environment. AIXI is generally the optimal agent according to this score, but there may be reasons to analyze other agents and compare score values. If we want to use this definition of intelligence in practice, perhaps we can start by analyzing some simple agents. Common algorithms can be thought of as simple agents (environment is input, reward is based on running time) so we take the goal of applying the agent intelligence score to algorithms. That is, we want to find, what are the IQ scores of algorithms? We can do some very simple analysis, but the real answer is that even for simple algorithms, the intelligence score is too difficult to work with in practice.
The current work addresses a virtual environment with self-replicating agents whose decisions are based on a form of "somatic computation" (soma - body) in which basic emotional responses, taken in parallelism to actual living organisms, are introduced as a way to provide the agents with greater reflexive abilities. The work provides a contribution to the field of Artificial Intelligence (AI) and Artificial Life (ALife) in connection to a neurobiology-based cognitive framework for artificial systems and virtual environments' simulations. The performance of the agents capable of emotional responses is compared with that of self-replicating automata, and the implications of research on emotions and AI, in connection to both virtual agents as well as robots, is addressed regarding possible future directions and applications.
The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body as self-cells or non-self cells. It does this with the help of a distributed task force that has the intelligence to take action from a local and also a global perspective using its network of chemical messengers for communication. There are two major branches of the immune system. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms, whilst the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time. This remarkable information processing biological system has caught the attention of computer science in recent years. A novel computational intelligence technique, inspired by immunology, has emerged, called Artificial Immune Systems. Several concepts from the immune have been extracted and applied for solution to real world science and engineering problems. In this tutorial, we briefly describe the immune system metaphors that are relevant to existing Artificial Immune Systems methods. We will then show illustrative real-world problems suitable for Artificial Immune Systems and give a step-by-step algorithm walkthrough for one such problem. A comparison of the Artificial Immune Systems to other well-known algorithms, areas for future work, tips & tricks and a list of resources will round this tutorial off. It should be noted that as Artificial Immune Systems is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from time to time and from those examples given here.
This paper illustrates how a Prolog program, using chronological backtracking to find a solution in some search space, can be enhanced to perform intelligent backtracking. The enhancement crucially relies on the impurity of Prolog that allows a program to store information when a dead end is reached. To illustrate the technique, a simple search program is enhanced.   To appear in Theory and Practice of Logic Programming.   Keywords: intelligent backtracking, dependency-directed backtracking, backjumping, conflict-directed backjumping, nogood sets, look-back.
In this study, we reproduce two new hybrid intelligent systems, involve three prominent intelligent computing and approximate reasoning methods: Self Organizing feature Map (SOM), Neruo-Fuzzy Inference System and Rough Set Theory (RST),called SONFIS and SORST. We show how our algorithms can be construed as a linkage of government-society interactions, where government catches various states of behaviors: solid (absolute) or flexible. So, transition of society, by changing of connectivity parameters (noise) from order to disorder is inferred.
A society's single emergent, increasing intelligence arises partly from the thermodynamic advantages of networking the innate intelligence of different individuals, and partly from the accumulation of solved problems. Economic growth is proportional to the square of the network entropy of a society's population times the network entropy of the number of the society's solved problems.
The World Wide Web (WWW) allows the people to share the information (data) from the large database repositories globally. The amount of information grows billions of databases. We need to search the information will specialize tools known generically search engine. There are many of search engines available today, retrieving meaningful information is difficult. However to overcome this problem in search engines to retrieve meaningful information intelligently, semantic web technologies are playing a major role. In this paper we present survey on the search engine generations and the role of search engines in intelligent web and semantic search technologies.
Informledge System (ILS) is a knowledge network with autonomous nodes and intelligent links that integrate and structure the pieces of knowledge. In this paper, we aim to put forward the link dynamics involved in intelligent processing of information in ILS. There has been advancement in knowledge management field which involve managing information in databases from a single domain. ILS works with information from multiple domains stored in distributed way in the autonomous nodes termed as Knowledge Network Node (KNN). Along with the concept under consideration, KNNs store the processed information linking concepts and processors leading to the appropriate processing of information.
Location management refers to the problem of updating and searching the current location of mobile nodes in a wireless network. To make it efficient, the sum of update costs of location database must be minimized. Previous work relying on fixed location databases is unable to fully exploit the knowledge of user mobility patterns in the system so as to achieve this minimization. The study presents an intelligent location management approach which has interacts between intelligent information system and knowledge-base technologies, so we can dynamically change the user patterns and reduce the transition between the VLR and HLR. The study provides algorithms are ability to handle location registration and call delivery
This paper introduces a new computing model based on the cooperation among Turing machines called orchestrated machines. Like universal Turing machines, orchestrated machines are also designed to simulate Turing machines but they can also modify the original operation of the included Turing machines to create a new layer of some kind of collective behavior. Using this new model we can define some interested notions related to cooperation ability of Turing machines such as the intelligence quotient or the emotional intelligence quotient for Turing machines.
Imprecise-information processing will play an indispensable role in intelligent systems, especially in the anthropomorphic intelligent systems (as intelligent robots). A new theoretical and technological system of imprecise-information processing has been founded in Principles of Imprecise-Information Processing: A New Theoretical and Technological System[1] which is different from fuzzy technology. The system has clear hierarchy and rigorous structure, which results from the formation principle of imprecise information and has solid mathematical and logical bases, and which has many advantages beyond fuzzy technology. The system provides a technological platform for relevant applications and lays a theoretical foundation for further research.
IQ tests are an accepted method for assessing human intelligence. The tests consist of several parts that must be solved under a time constraint. Of all the tested abilities, pattern recognition has been found to have the highest correlation with general intelligence. This is primarily because pattern recognition is the ability to find order in a noisy environment, a necessary skill for intelligent agents. In this paper, we propose a convolutional neural network (CNN) model for solving geometric pattern recognition problems. The CNN receives as input multiple ordered input images and outputs the next image according to the pattern. Our CNN is able to solve problems involving rotation, reflection, color, size and shape patterns and score within the top 5% of human performance.
This paper describes an approach to the design of a population of cooperative robots based on concepts borrowed from Systems Theory and Artificial Intelligence. The research has been developed under the SocRob project, carried out by the Intelligent Systems Laboratory at the Institute for Systems and Robotics - Instituto Superior Tecnico (ISR/IST) in Lisbon. The acronym of the project stands both for "Society of Robots" and "Soccer Robots", the case study where we are testing our population of robots. Designing soccer robots is a very challenging problem, where the robots must act not only to shoot a ball towards the goal, but also to detect and avoid static (walls, stopped robots) and dynamic (moving robots) obstacles. Furthermore, they must cooperate to defeat an opposing team. Our past and current research in soccer robotics includes cooperative sensor fusion for world modeling, object recognition and tracking, robot navigation, multi-robot distributed task planning and coordination, including cooperative reinforcement learning in cooperative and adversarial environments, and behavior-based architectures for real time task execution of cooperating robot teams.
We present a case study of artificial intelligence techniques applied to the control of production printing equipment. Like many other real-world applications, this complex domain requires high-speed autonomous decision-making and robust continual operation. To our knowledge, this work represents the first successful industrial application of embedded domain-independent temporal planning. Our system handles execution failures and multi-objective preferences. At its heart is an on-line algorithm that combines techniques from state-space planning and partial-order scheduling. We suggest that this general architecture may prove useful in other applications as more intelligent systems operate in continual, on-line settings. Our system has been used to drive several commercial prototypes and has enabled a new product architecture for our industrial partner. When compared with state-of-the-art off-line planners, our system is hundreds of times faster and often finds better plans. Our experience demonstrates that domain-independent AI planning based on heuristic search can flexibly handle time, resources, replanning, and multiple objectives in a high-speed practical application without requiring hand-coded control knowledge.
This article is an attempt to combine different ways of working with sets of objects and their classes for designing and development of artificial intelligent systems (AIS) of analysis information, using object-oriented programming (OOP). This paper contains analysis of basic concepts of OOP and their relation with set theory and artificial intelligence (AI). Process of sets and multisets creation from different sides, in particular mathematical set theory, OOP and AI is considered. Definition of object and its properties, homogeneous and inhomogeneous classes of objects, set of objects, multiset of objects and constructive methods of their creation and classification are proposed. In addition, necessity of some extension of existing OOP tools for the purpose of practical implementation AIS of analysis information, using proposed approach, is shown.
In this paper, we propose a new methodology based on the Negative Selection Algorithm that belongs to the field of Computational Intelligence, specifically, Artificial Immune Systems to identify takeover targets. Although considerable research based on customary statistical techniques and some contemporary Computational Intelligence techniques have been devoted to identify takeover targets, most of the existing studies are based upon multiple previous mergers and acquisitions. Contrary to previous research, the novelty of this proposal