A graduate text teaching machine learning through a unified Bayesian lens, treating classification, regression, and clustering as inference over distributions. Covers graphical models, EM, kernels, and approximate inference with derivations.
Frames machine learning through the lens of statistics, treating each method as an estimator with bias, variance, and inferential meaning, not a black box. Covers linear models through boosting, SVMs, and graphical models, math made explicit.
Gives intelligence a falsifiable mathematical definition — an agent's expected reward across all computable environments, weighted by simplicity — turning a fuzzy word into the Universal Intelligence Measure built on AIXI and Solomonoff induction.
Graduate-level ML textbook that frames nearly every method as Bayesian inference under one probabilistic lens, from linear models to deep nets and graphical models. Encyclopedic at ~1100 pages, math-heavy, with MATLAB code.
Embodied AI2013
Open textbook for upper-level undergraduates that explains computational principles behind autonomous robots — mechanisms, sensors, actuators, perception, and planning — with exercises and simulation assets. Distributed as LaTeX source under a CC-BY-NC-ND license and accompanied by course materials and Webots examples.
Builds deep learning from the ground up, first teaching the linear algebra, probability, and numerical methods most ML texts assume you know. Three parts run from math foundations to practical networks to research topics, favoring reasoning over recipes.
Provides 150+ executed Jupyter notebooks and code that reproduce the book 'Machine Learning for Algorithmic Trading (2nd ed.)' — covers feature engineering, alternative-data signal extraction, backtesting, NLP, deep learning and reinforcement learning for trading; best for quant researchers and practitioners.
Notebook-first deep learning textbook that teaches concepts through runnable multi-framework code, math, and exercises. Includes lecture-ready notebooks, community contributions, and broad university adoption—designed for hands-on learners and instructors.
Graduate-level textbook unifying classical statistics and modern deep learning under one probabilistic framework. Builds from probability, information theory, and optimization up to neural nets, with runnable Python/JAX figure code and exercise solutions.
Builds a single rigorous theory from one question: why some bit strings look random. Defines plain and prefix complexity, the incompressibility method, and Martin-Löf randomness, tying information content to whether a short program can reproduce a string.
A free, open textbook on engineering ML systems — building efficient, reliable AI from a single GPU up to warehouse-scale clusters. Goes beyond model design and MLOps tooling to the underlying science: scheduling, quantization, data pipelines, serving.
Reworks the classic Bishop PRML for the deep learning era, adding dedicated chapters on transformers and diffusion models. Builds each idea from probability up using text, diagrams, math, and pseudocode, aimed at readers new to the field.