Often considered the definitive all-around AI textbook, covering classical AI through modern topics with broad scope and strong pedagogy.
The go-to deep learning reference that systematized neural network theory and practice for researchers and advanced practitioners.
A classic for probabilistic machine learning and statistical pattern recognition; influential for Bayesian methods and graphical models.
The standard text for reinforcement learning, laying out core algorithms and concepts used across robotics, games, and decision-making systems.
A deep, rigorous treatment of graphical models—central for reasoning under uncertainty, structured prediction, and probabilistic inference.
A uniquely readable and wide-ranging text connecting information theory, Bayesian inference, and learning, with intuition-forward explanations.
A comprehensive, modern ML reference with a strongly probabilistic framing and broad topic coverage used widely in graduate study.
The canonical NLP book: foundational methods through modern neural approaches, plus linguistic and evaluation grounding.
An accessible, big-picture tour of major ML paradigms and the idea of a unifying ‘master algorithm,’ aimed at general readers and practitioners.
A widely read critique of how models can cause harm at scale, helping AI practitioners think about bias, accountability, and real-world impacts.
