MATH 3035U – Mathematics of Machine Learning

This course surveys the mathematics required for Machine Learning. The course will introduce a number of Machine Learning techniques and discuss the mathematical principles that are necessary for the understanding and efficient implementation of the techniques. Topics may include: Linear Regression, Logistic Regression, Principle Component Analysis, Neural Networks, matrix factorization, singular value decomposition, leastsquares, maximum likelihood estimation, continuous and numerical optimization, gradient descent, back propagation and computation with large matrices.
Credit hours: 3
Lecture hours: 3
Laboratory hours: 0
Tutorial hours: 0
Other hours: 0
Prerequisite(s): (MATH 2050U and MATH 2072U) or (CSCI 2072U and STAT 2010U)
Recommended: MATH 2015U