[
  {
    "path": "README.md",
    "content": "# 📚 AI / ML Bookshelf\n\nWelcome to my personal reference shelf of **freely shareable** AI & Machine-Learning books.  \nI keep the PDFs here so I can grep formulas, revisit algorithms, and point friends straight to the good stuff.\n\n---\n\n## Table of contents\n\n| # | Title | Snapshot |\n|---|-------|----------|\n| 1 | **[Deep Learning Interviews](./1.Deep%20learning%20Interviews.pdf)** | 400 + curated Q&As spanning CNNs, transformers, maths and system design—perfect for pre-interview rapid-fire revision. |\n| 2 | **[Foundation of LLM.pdf](./2.Foundation%20of%20LLM.pdf)** | A newcomer-friendly primer on how large language models are built, trained and aligned, from tokenization to safety. |\n| 3 | **[Reinforcement Learning – An Overview](./3.Reinforcement%20Learning-%20An%20Overview.pdf)** | A panoramic survey of modern RL: value-based, policy-gradient, model-based and hybrid methods, with practical tips and further reading. |\n| 4 | **[Alg4ai.pdf](./4.alg4ai.pdf)** | Concise Stanford-style notes covering search, constraint satisfaction, probabilistic reasoning and planning in ~150 pages. |\n| 5 | **[Math4ml.pdf](./5.math4ml.pdf)** | Linear algebra, calculus and probability essentials explained for ML practitioners, loaded with intuitive worked examples. |\n| 6 | **[OpenAI guide to building practical agents](./6.openAI%20guide%20to%20building%20practical%20agents.pdf)** | Design patterns, orchestration tricks and guardrails for shipping real-world AI agents with the OpenAI tool-chain. |\n| 7 | **[Pen and paper exercise in ML](./7.pen%20and%20paper%20exercise%20in%20ML.pdf)** | A workbook of theory-first problems (with solutions) to deepen mathematical intuition—no keyboard required. |\n| 8 | **[Matrixcookbook](./8.matrixcookbook.pdf)** | A concise “cheat-sheet” of hundreds of matrix identities, derivatives, decompositions, and statistical formulas you’ll reach for whenever linear-algebra algebra gets hairy; perfect as a desktop reference to speed up proofs and ML math. |\n| 9 |**[Finetuning guide](./9.finetuning%20guide.pdf)** | The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities. |\n| 10 |**[MULTI-AGENT REINFORCEMENT LEARNING](./10.marl-book.pdf)** | A definitive introduction to multi-agent reinforcement learning, this book blends game theory and deep learning to offer both foundational insights and cutting-edge research—ideal for newcomers and experts alike. | \n| 11 |**[Context Engineering](./11.context-engineering.pdf)** | A comprehensive 150+ pages survey on context engineering|\n| 12 |**[Linear Algebra Essence and form book](./12.LAEF.pdf)** | A linear algebra book that connects to concepts in AI |\n| 13 |**[Machine Learning Systems](./13.Machine-Learning-Systems.pdf)** | A comprehensive, up-to-date guide from Harvard on ML Systems Engineering — covering everything from deep learning foundations to distributed training, model optimization, and emerging AGI-scale systems. |\n \n\n\n---\n\n## How to use\n\n1. **Clone** the repo  \n   ```bash\n   git clone https://github.com/AniruddhaChattopadhyay/Books.git\n\n2. Open any PDF in your favourite reader—or preview directly on GitHub.\n\n3. Search the folder (ripgrep, Spotlight, etc.) when you half-remember that derivation.\n\n4. ⭐ **Star** the repo to catch new additions whenever I find a gem.\n\n## Contributing\nHave a legally distributable AI/ML book that belongs here?\nOpen a PR with the PDF and add a two-line description to this table. No pay-walled or pirated material, please.\n\n## License & attribution\nEach PDF retains its original license (usually CC-BY-NC or similar)—see inside the book for details.\nThis README and folder structure are released under the MIT License.\n\nAll materials are publicly available under the authors’ distribution terms. If a publisher requests removal, I will comply immediately. Support the authors—buy the print editions or leave reviews if you find these texts valuable.\n\nHappy reading & building! 🚀\n\n"
  }
]