Foundations Machine Learning

Credits	4
Tags	Machine Learning Programming
Key Topics	Machine Learning, Linear Regression, Neural Networks, Optmization
Prerequisites	MATH 1910, MATH 2940, ECE 3100 (or equivalents).
Course Tags	Last offered: SP25

Class Overview

This course provides an introduction to machine learning that covers basic theory, algorithms, and applications. Topics include learning theory, which covers the statistical learning paradigm, empirical risk minimization, generalization, bias-variance tradeoff, regularization, and validation, supervised learning, which covers regression, the maximum likelihood principle, generalized linear models, support vector machines, and naïve Bayes, and unsupervised learning, which includes clustering, kmeans, EM algorithm, factor analysis, and other dimensionality reduction techniques.

Professor: Dr. Ziv Golfeld

Semester(s): Spring

Difficulty: 4/5

Rating: 5/5

Assignments: Weekly problem sets which include a coding part, and one competition held on Kaggle.

Exams: One prelim and one final exam.

Pros

Well-organized class with applicable material.
Helpful instructor and lots of academic support available (6 weekly OH slots).
Homeworks and exams relate directly to class content.

Cons

Challenging problem sets that take more than expected.
Difficult course content, the notation can be unfamiliar.

Tips for Success

Ask questions in lecture and attend office hours
Start working on the coding homewrok parts early.
Carefully review material before exams.