Data-Driven Modeling and Machine Learning

4 credits

Practical introduction to machine learning methods emphasizing high-level understanding as well as hands-on experience with machine-learning frameworks. Topics include supervised and unsupervised learning, neural networks and deep learning, and reinforcement learning. Applications drawn from areas such as statistics, decision-making and control, signal processing, and scientific computing. Course overlaps with: TEE 440 and TSTAT 336. Prerequisite: either MATH 126 or MATH 136; and either E E 241 or CSE 163.