If I was learning AI from scratch today, these are the 21 books I’d be buying.
Whether you're building your first model or designing production AI systems, this list covers the full stack of AI knowledge.
Core AI & ML
- AI Engineering, Chip Huyen
- Machine Learning, Peter Flach
- Artificial Intelligence: A Modern Approach, Stuart Russell & Peter Norvig
- Introduction to Evolutionary Computing, A.E. Eiben & J.E. Smith
Deep Learning & RL
- Deep Learning, Ian Goodfellow, Yoshua Bengio & Aaron Courville
- Reinforcement Learning: An Introduction, Richard S. Sutton & Andrew Barto
- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, Aurélien Géron
- Deep Learning for Coders with fastai and PyTorch, Jeremy Howard & Sylvain Gugger
- Dive into Deep Learning, Aston Zhang, Zachary C. Lipton, Mu Li & Alexander J. Smola
NLP / LLMs
- Natural Language Processing with Transformers, Lewis Tunstall, Leandro von Werra & Thomas Wolf
- Build a Large Language Model (From Scratch), Sebastian Raschka
Generative Deep Learning, David Foster
Computer Vision
- Computer Vision: Algorithms and Applications, Richard Szeliski
MLOps / Production ML
- Designing Machine Learning Systems, Chip Huyen
- Machine Learning Design Patterns, Valliappa Lakshmanan, Sara Robinson & Michael Munn
- Reliable Machine Learning, Cathy Chen, Martin Musiari, et al.
Optimization & Search
- Convex Optimization, Stephen Boyd & Lieven Vandenberghe
- Algorithms for Optimization, Mykel J. Kochenderfer & Tim A. Wheeler
Math & Statistical Foundations
- Mathematics for Machine Learning, Marc Peter Deisenroth, A. Aldo Faber & - Cheng Soon Ong
- The Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani & Jerome Friedman
- An Introduction to Statistical Learning, Gareth James, Daniela Witten, Trevor Hastie & Robert Tibshirani
You don't need to read all 21. Pick the area you’re interested in and start there.
The best engineers I know never stop learning.
