[
  {
    "path": "README.md",
    "content": "# AI-reading-list\nThis is my personal  list of current AI papers I'm reading/ have yet to read. Just things I think point in interesting directions, or topics I'm interested in. \n\n## General\n[Tensorflow](http://download.tensorflow.org/paper/whitepaper2015.pdf) - Google's large scale infrastructure project\n\n[Representation learning](http://arxiv.org/abs/1206.5538) - survey paper on representation methods\n\n[Adversarial Networks](http://arxiv.org/abs/1406.2661) - framework for generation\n\n[Neural Turing Machine](http://arxiv.org/abs/1410.5401)\n\n\n## RNN structures \n[LTSM](http://web.eecs.utk.edu/~itamar/courses/ECE-692/Bobby_paper1.pdf) - long term short term memory\n\n[Memory Networks](http://arxiv.org/abs/1410.3916/) - on adding memory storage\n\n[End to End Memory networks](http://arxiv.org/abs/1503.08895) - Facebook's memory storage\n\n[Neural Programmer](http://arxiv.org/abs/1511.04834) - on adding basic artithmetic operations\n\n[Spatial Transformer](http://arxiv.org/abs/1509.05329) - DeepMind digit classification\n\n[Deep Speech](http://arxiv.org/abs/1412.5567) - speech implementation\n\n## Word Vectors\n[word2vec](http://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf) - on creating vectors to represent language, useful for RNN inputs\n\n[sense2vec](http://arxiv.org/abs/1511.06388) - on word sense disambiguation\n\n[Infinite Dimensional Word Embeddings](http://arxiv.org/abs/1511.05392) - new\n\n[Skip Thought Vectors](http://arxiv.org/abs/1506.06726) - word representation method\n\n[Adaptive skip-gram](http://arxiv.org/abs/1502.07257) - similar approach, with adaptive properties\n\n## Natural Language\n[Neural autocoder for paragraphs and documents](http://arxiv.org/abs/1506.01057) - LTSM representation\n\n[LTSM over tree structures](http://arxiv.org/abs/1503.04881)\n\n[Sequence to Sequence Learning](http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf) - word vectors for machine translation\n\n[Teaching Machines to Read and Comprehend](http://arxiv.org/abs/1506.03340) - DeepMind paper\n\n## Convolutional neural nets\n[DRAW](http://jmlr.org/proceedings/papers/v37/gregor15.pdf)- An RNN for image classfication\n\n[ImageNet Classification](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks) - popular paper\n\n[A Neural Algorithm of Artistic Style](http://arxiv.org/pdf/1508.06576v1.pdf) - popular papeer\n\n[Generative Adversarial Networks](http://arxiv.org/abs/1511.06434) - unsupervised learning to generate images\n\n##Tutorials\n[LTSM RNN in Python](http://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/)\n\n[Tensorflow Tutorials](https://github.com/nlintz/TensorFlow-Tutorials)\n\n[K-Means with Tensorflow](https://codesachin.wordpress.com/2015/11/14/k-means-clustering-with-tensorflow/)\n\n##Datasets\n\n[DeepMind Q&A Corpus](https://github.com/deepmind/rc-data/)\n"
  }
]