Statistical Machine Learning

Graduate credit

This course covers methods for modern multivariate data analysis and statistical learning, including both their theoretical foundations and practical applications. Topics include principal component analysis and other dimension reduction techniques, classification (discriminant analysis, nearest neighbor classifiers, logistic regression, support vector machines, decision trees, ensemble methods, neural networks), clustering (k-means, hierarchical clustering, model-based methods, spectral clustering), and some basics of reinforcement learning. The objective is to learn what methods are available for statistical machine learning, how to use them, and when they should and should not be applied. There will be a significant data analysis component.