Essential AI/ML Books

Theoretical Foundations

Deep Learning

  • Authors: Ian Goodfellow, Yoshua Bengio, Aaron Courville
  • Publisher: MIT Press · 2016
  • Free PDF: https:/ww.deeplearningbook.org/
  • Covers: backprop, CNNs, RNNs, unsupervised models, mathematical foundations

Pattern Recognition and Machine Learning

  • Authors: Christopher M. Bishop
  • Publisher: Springer · 2006
  • Covers: probabilistic graphical models, Bayesian methods, variational inference

Machine Learning: A Probabilistic Perspective

  • Authors: Kevin P. Murphy
  • Publisher: MIT Press · 2012
  • Covers: classical and probabilistic ML, graphs, Monte Carlo — complete theoretical reference

Probabilistic Machine Learning (vols. 1 and 2)

  • Authors: Kevin P. Murphy
  • Publisher: MIT Press · 2022/2023
  • Free PDF: https:/robml.github.iopml-book
  • Covers: modern, expanded version of the previous one; includes deep learning and LLMs

Reinforcement Learning: An Introduction

  • Authors: Richard S. Sutton & Andrew G. Barto
  • Publisher: MIT Press · 2018 (2nd ed.)
  • Free PDF: http:/ncompleteideas.netbookthe-book-2nd.html
  • Covers: DP, TD learning, Q-learning, policy gradients — standard RL reference

Mathematics for Machine Learning

  • Authors: Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
  • Publisher: Cambridge University Press · 2020
  • Free PDF: https:/ml-book.github.io/
  • Covers: linear algebra, calculus, probability, optimization — mathematical foundation

The Elements of Statistical Learning

  • Authors: Trevor Hastie, Robert Tibshirani, Jerome Friedman
  • Publisher: Springer · 2009 (2nd ed.)
  • Free PDF: https:/astie.su.domainsElemStatLearn
  • Covers: classical ML: trees, SVMs, boosting, shallow neural networks

Neural Networks and Deep Learning

  • Authors: Michael Nielsen
  • Free online: http:/euralnetworksanddeeplearning.com/
  • Covers: accessible introduction — backprop, CNNs, regularization

Books on LLMs and Modern AI

Build a Large Language Model (From Scratch)

  • Authors: Sebastian Raschka
  • Publisher: Manning · 2024
  • Covers: practical implementation of an LLM from scratch in PyTorch — highly recommended

Designing Machine Learning Systems

  • Authors: Chip Huyen
  • Publisher: O'Reilly · 2022
  • Covers: MLOps, data pipelines, deployment, production monitoring

Natural Language Processing with Transformers

  • Authors: Lewis Tunstall, Leandro von Werra, Thomas Wolf
  • Publisher: O'Reilly · 2022
  • Free PDF: https:/ransformersbook.com/
  • Covers: practical fine-tuning with HuggingFace Transformers

The RLHF Book

  • Authors: Nathan Lambert
  • Free online: https:/lhfbook.com/
  • Covers: complete RLHF — reward models, PPO, DPO, alignment

Permanent Online Resources

Resource URL Focus
Andrej Karpathy — Neural Networks: Zero to Hero youtube.com/@karpathy Practical LLM implementation
fast.ai — Practical Deep Learning fast.ai Applied DL, top-down
Stanford CS229 (ML) cs229.stanford.edu ML foundations
Stanford CS224N (NLP) cs224n.stanford.edu NLP and Transformers
Stanford CS336 (LLMs) cs336.stanford.edu LLMs from scratch (2024)
Hugging Face Course huggingface.co/learn Practical, HF ecosystem
Lilian Weng's Blog lilianweng.github.io Excellent technical summaries
Sebastian Raschka's Blog magazine.sebastianraschka.com LLMs, fine-tuning, papers