MATH 165 - (MA) Statistical Learning

Semester Hours: 3

This course develops the fundamental ideas of statistical learning for drawing conclusions from multivariate data sets using statistical theory and applied linear algebra.  The course combines a theoretical presentation with computation of the resulting algorithms on real data sets to develop intuition of both how the methods work and how they perform in practice.  It will cover the major techniques and concepts for supervised learning.  Topics will include linear regression, classification, resampling methods, model selection, and regularization. For non-linear methods, polynomial regression, general additive models, random forests and deep learning with neural networks.  We will also cover survival analysis, censored data and multiple testing.

Prerequisite(s)/Course Notes:
MATH 138  or CSC 186 , MATH 085  or both MATH 073  and MATH 135A , and CSC 174 

View Course Offering(s):

Fall 2025

January 2026

Spring 2026