Supervised Learning - STAT 841 Fall 2017

Explore supervised learning fundamentals through this comprehensive university-level course covering essential machine learning algorithms and techniques. Master linear and quadratic discriminant analysis (LDA, QDA), principal component analysis (PCA), and Fisher discriminant analysis (FDA) as foundational methods. Delve into logistic regression, model selection strategies, and neural networks including backpropagation and radial basis networks (RBN). Learn complexity control techniques, regularization methods, and support vector machines (SVM) including hard margin, soft margin, and kernel SVM approaches. Discover metric learning principles, sparse principal component analysis (SPCA), and classical algorithms like Naive Bayes and k-nearest neighbors. Advance to modern deep learning with convolutional neural networks, random features, decision trees, and ensemble methods like bagging, gaining both theoretical understanding and practical implementation skills across the supervised learning landscape.