Machine Learning

Catalog description

Fundamentals of applied machine learning using Python, Scikit-Learn, and a modern deep learning framework. This course takes a project-based hands-on approach with a focus on using existing tools and libraries to solve problems, rather than developing ML algorithms from scratch.  Topics include supervised learning (classification and regression) and unsupervised learning (clustering and dimensionality reduction), as well as semi-supervised and self-supervised ML.  Applications may be drawn from areas such as computer vision, natural language processing, business data mining, recommendation systems, and cybersecurity.  Prerequisites: CSC 201, MATH 160 and one of the following statistics classes MATH 330, BUSN 211, PSYCH 240, SOAN-227, or MATH 130.