All courses
8 courses in four subjects. Each one is self-paced, free, and runs its own Python in the browser. Not sure where to begin? Follow the guided path.
Foundations
Linear AlgebraVectors, matrix factorizations, and eigendecomposition from first principles — the mathematical foundation every other course in this catalog assumes.Probability & StatisticsProbability, conditioning, and estimation for machine learning — from random variables and Bayes to MLE/MAP, uncertainty, and the language of modern generative and RL models.
Optimization
OptimizationFirst-order methods and convex toolkit for training models — from gradient descent to Adam, with enough convexity to know what your optimizer can and cannot guarantee.Advanced OptimizationBoyd-depth duality and cone programs meet second-order, distributed, and sharpness-aware training — the bridge from convex structure to modern large-scale ML optimization.
Machine learning
Robotics
Robot LearningImitation learning, behaviour cloning, and sim-to-real transfer. Build controllers that learn from demonstration and adapt to reality.Physical AI & Vision-Language ModelsFrom vision backbones to embodied agents — how language and perception fuse into systems that act in the physical world.