Foundations of Machine Learning

Graduate

Students will learn the introduction background and foundation of machine learning. Topics may include: matrix algebra, probability theory, multivariable calculus, information theory, algorithms and complexity, intractability, computational learning theory, optimization, Bayesian learning, linear methods, support vector machines, kernels, dimensionality reduction, matrix decomposition and factorization, clustering, performance evaluation, regression, decision trees, and neural networks. Topics also include legal, societal and ethical implications of machine learning. (This is an experiential course.)