Theory of Machine Learning - 625.742

This course introduces various machine learning algorithms with emphasis on their derivation and underlying mathematical theory. Topics include the mathematical theory of linear models (regression and classification), anomaly detectors, tree-based methods, regularization, fully connected neural networks, convolutional neural networks, and model assessment. Students will gain experience in formulating models and implementing algorithms using Python. Students will need to be comfortable with writing code in Python to be successful in this course. At the end of this course, students will be able to implement, apply, and mathematically analyze a variety of machine learning algorithms when applied to real-world data. Course Note(s): Although students will have coding assignments, this course differs from other EP machine learning courses in that the primary focus is on the mathematical foundations underlying the algorithms.

Course Prerequisite(s)

Multivariate calculus, linear algebra (e.g. EN.625.609), and probability and statistics (EN.625.603 or similar course). Comfort with reading and writing mathematical proofs would be helpful but is not required.;Students cannot receive credit for both EN.605.746 and EN.625.742