04-650 Mathematical Foundations of Machine Learning

12 units, Carnegie Mellon University

The class reviews some of the math concepts on which most of machine learning models are built. The topics covered in this class include major concepts in linear algebra and analytic geometry (e.g., linear mapping, norms, distances, inner products, determinants and trace, eigenvectors and eigenvalues, matrix decomposition), vector calculus (e.g., differentiation, gradients), intro to probability and statistics (e.g., multivariate random variable, MLE, MAP, etc., ), and optimization theory if time permits (e.g., convex function, gradient-based optimization, constrained optimization, etc.). The homework will include a mix of math problems and some modest implementation in Python, or MATLAB.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.