Mathematics of Machine Learning

Catalog description

Machine learning is the study of algorithms (e.g. gradient descent) that learn functions (e.g. deep networks) from experience (e.g. data). Behind this simple statement is a lot of mathematical scaffolding: statistics for handling data, optimization for understanding learning algorithms, and linear algebra to create expressive models. This course provides the background to be able to understand mathematical concepts commonly used in machine learning. Topics include continuous probability, parametric distributions, and concentration inequalities from statistics; inner product spaces, functional analysis and Hilbert spaces from linear algebra; and multivariate calculus, Taylor’s theorem, and convexity from optimization.