Machine Learning

This is an introductory undergraduate course in Machine Learning, a cutting-edge subfield of computer science research concerned with developing algorithms to learn from data. Machine learning is at the foundation of data science. A wide range of technologies rely on machine learning techniques, including web search, recommendation systems for books, movies, and music, and personalized internet advertising, deployed on search engines, mobile phones, and social networking applications. Machine learning has also made profound impacts on problems as varied as DNA analysis, computer vision, and natural language processing, among others.

The course will provide a technical overview of core machine learning topics, including: nearest-neighbor techniques, regression, classification, perceptron, kernel methods, support vector machines (SVM), logistic regression, ensemble methods including boosting, graphical models including hidden Markov models (HMM), non-parametric methods, neural networks and deep learning, online learning, active learning, unsupervised learning including clustering, feature selection, parameter tuning, cross-validation, and ethical considerations. Topics are subject to changes and adjustments.