Statistical Machine Learning

3 Hours

Introduction to the theoretical underpinnings of machine learning and the derivations that transform those foundations into practical algorithms. Discuss empirical risk minimization and the probably approximately correct (PAC) learning framework; the bias-complexity tradeoff; the Vapnik-Chervonenkis dimension; Rademacher complexities; linear predictors; boosting; model selection and validation; convex learning problems; support vector machines and kernel methods; decision trees; clustering; dimensionality reduction; generative models; and variational Bayesian methods. Only one of the following may be counted: Electrical and Computer Engineering 381K (Topic 4), Electrical and Computer Engineering 381V (Topic: Statistical Machine Learning) and Electrical Engineering 381V (Topic: Statistical Machine Learning).