Textbooks rebuilt as interactive experiences. Every chapter condensed into a hands-on lesson with simulations, visualizations, and quizzes. The book becomes alive.
The definitive textbook on RL, from multi-armed bandits to policy gradients. Every chapter rebuilt as an interactive lesson with live simulations.
From probabilistic reasoning to multiagent systems. Every algorithm derived, visualized, and made interactive. The complete decision-making toolkit.
How do you prove an autonomous system is safe? Falsification, reachability analysis, importance sampling, explainability, and runtime monitoring.
The mathematical foundations every ML practitioner needs. Linear algebra, calculus, probability, optimization, then applied to regression, PCA, GMMs, and SVMs.
Data, tensor, pipeline, context, and expert parallelism. The complete playbook for distributed training at scale.
Training and serving LLMs on TPUs and GPUs — roofline analysis, transformer math, parallelism strategies, and inference optimization.
Classical robotics to VLAs — FK/IK, RL, imitation learning (ACT, Diffusion Policy), and generalist policies (π0, SmolVLA). All with LeRobot code.
Vectors, forces, particle systems, autonomous agents, cellular automata, fractals, genetic algorithms, neural networks.
Coordinate frames, Kalman filtering, inertial sensors, GNSS, INS/GNSS integration, fault detection.
From bracketing to Bayesian optimization. Gradient, direct, stochastic, population methods. LP, QP, surrogates.
Bayes filters, Kalman/particle filters, localization, mapping, SLAM, motion planning under uncertainty.
The definitive motion planning textbook. Discrete planning, configuration spaces, RRTs, PRMs, decision theory, differential constraints. From grid search to information spaces.
Probability, linear models, neural nets, kernels, SVMs, graphical models, EM, sampling, PCA, HMMs.
Type deduction, auto, smart pointers, move semantics, lambdas, concurrency. 42 best practices for C++11/14.
Projective geometry, camera models, epipolar geometry, fundamental matrix, triangulation, reconstruction.
Image processing, deep learning, recognition, features, stitching, motion, computational photography, 3D.
Data structures, sorting, graph traversal, weighted graphs, combinatorial search, dynamic programming, NP.
Fork, signals, pipes, FIFOs, file locking, message queues, semaphores, shared memory, mmap, Unix sockets.
Variables, strings, functions, classes, containers, algorithms, dynamic memory, copy control, OOP, templates.
ODEs, Laplace transforms, linear algebra, vector calculus, Fourier series, PDEs, complex analysis.
Linear algebra, probability, feedforward nets, regularization, optimization, CNNs, RNNs, applications.
Probability, statistics, logistic regression, deep networks, nonparametric methods, generative models.
Universal AI theory, AIXI, Kolmogorov complexity, a mathematical definition of intelligence, and the limits of computation. The thesis that co-founded DeepMind.
The shortest description of a string, the meaning of randomness, and the bridge between information theory and computability. From plain complexity to martingales.
The complete Stanford CS109 course reader. From counting and Bayes to CLT, bootstrapping, MLE, and machine learning — all with interactive simulations.
From noise to data via ODEs and SDEs. Flow matching, score matching, classifier-free guidance, DiT architectures, VAEs, and discrete diffusion for language.