Advanced Machine Learning

Catalog description

Explores models for regression, classification, clustering, and spans supervised, unsupervised, deep, and federated learning. Topics include linear regression, regularization, Bayesian networks, recurrent neural networks, large language models, distributed learning, and privacy-preserving machine learning. Students develop prediction models through a class project for engineering applications while incorporating performance metrics. Recommended: coursework in differential equations, linear/matrix algebra, multivariate calculus, and stochastic signal theory.