Mathematical Foundations of Machine Learning & AI
The mathematics behind modern AI in one course: learning as optimization, generalization, linear and logistic models, neural networks and backpropagation.
Zahri-Edu University › Mathematics for Machine Learning & AI
∇θ L
6 university courses · lecture notes, quizzes and exams.
The mathematics behind modern AI in one course: learning as optimization, generalization, linear and logistic models, neural networks and backpropagation.
Vectors and matrices as data, projections, least squares, eigendecomposition, SVD, PCA and low-rank approximation, with computational examples.
Gradients, Jacobians and Hessians, the chain rule on computational graphs, automatic differentiation and Taylor approximations of loss functions.
Maximum likelihood, Bayesian inference, the bias–variance trade-off, Gaussian models, information theory (entropy, KL divergence) and sampling.
Convex sets and functions, gradient and stochastic gradient methods, momentum and Adam, constrained optimization, duality and convergence rates.
Neural ODEs, gradient flows, diffusion and score-based generative models via SDEs, and physics-informed neural networks.
Exams and quizzes for these courses are in preparation.
In preparation: