Math for Machine Learning

3 credits · Graduate

The goal of this course is for students to internalize mathematical concepts that are crucial for learning machine learning topics such as supervised learning, dimensionality reduction, generative models, and neural network training. The topics covered include linear algebra (Euclidean vector space, matrix decomposition), probability theory (transformation of random variables, conditional probability, maximum likelihood estimation, and Markov chains), and vector calculus (gradients, backpropagation, and continuous optimization). Connections to relevant machine learning methods such as diffusion models will also be discussed.