Machine Learning

Catalog description

This course explores how to design and build software agents that are able to learn from experience and decide on courses of action without being explicitly programmed. Topics include regression algorithms, decision trees, support vector machines, neural networks, deep learning, Markov decision processes, and reinforcement learning. Emphasis is placed on algorithmic implementation. This course is taught largely at an undergraduate level. Graduate students have additional course requirements/expectations. Prerequisite: CS 340 ; MTH 207 ; junior standing. Offered Fall - Even Numbered Years.