awesome-artificial-intelligence

概要

厳選された人工知能リソースリスト。コース、書籍、ビデオ講義、論文を網羅。特にAIエンジニアリング実践に重点を置き、RAG、エージェント、評価、ガードレール、デプロイメントなどを扱う。

README プレビュー

# Awesome Artificial Intelligence\n\nA curated collection of **must-use, actively maintained resources** for building and shipping AI systems.\n\nFocus: **AI engineering** (RAG, agents, evals, guardrails, deploy) plus the best books, guides, papers, and a *carefully selected* set of tools.\n\n\n\n---\n\n## 📚 Learn\n_Deep, durable knowledge — still valuable five years from now._\n\n### Books\n**Modern & Practical**\n- [Designing Machine Learning Systems](https://www.oreilly.com/library/view/designing-machine-learning/9781098107956/) — Scalable, maintainable ML pipelines (Chip Huyen).\n- [AI Engineering](https://www.oreilly.com/library/view/ai-engineering/9781098166298/) — End-to-end AI product building (Chip Huyen).\n- [Build a Large Language Model from Scratch](https://www.manning.com/books/build-a-large-language-model-from-scratch) — Transformers in raw PyTorch, layer by layer (Sebastian Raschka).\n- [Hands-On Large Language Models](https://www.llm-book.com/) — Visual + practical guide to LLM applications (Jay Alammar, Maarten Grootendorst).\n- [LLM Engineer's Handbook](https://www.packtpub.com/en-us/product/llm-engineers-handbook-9781836200079) — Production LLMOps: fine-tuning, quantization, serving (Labonne, Iusztin).\n- [The 100-Page Language Models Book](https://www.thelmbook.com/) — Concise, math-grounded path from n-grams to transformers (Andriy Burkov).\n- [Generative Deep Learning (2nd Edition)](https://www.oreilly.com/library/view/generative-deep-learning/9781098134174/) — GANs, VAEs, diffusion models (David Foster).\n\n**Foundational**\n- [Artificial Intelligence: A Modern Approach](https://aima.cs.berkeley.edu/) — The canonical AI theory text (Russell, Norvig).\n- [Deep Learning](https://www.deeplearningbook.org/) — Mathematical foundations of neural networks (Goodfellow, Bengio, Courville).\n- [Deep Learning: Foundations and Concepts](https://www.bishopbook.com/) — Bishop's 2024 update; probability-grounded modern DL (Bishop & Bishop).\n- [Understandin