MATH 462. Machine Learning .
Credits: 3
Offered by: Mathematics and Statistics (Faculty of Science)
This course is not offered this catalogue year.
Description
Introduction to supervised learning: decision trees, nearest neighbors, linear models, neural networks. Probabilistic learning: logistic regression, Bayesian methods, naive Bayes. Classification with linear models and convex losses. Unsupervised learning: PCA, k-means, encoders, and decoders. Statistical learning theory: PAC learning and VC dimension. Training models with gradient descent and stochastic gradient descent. Deep neural networks. Selected topics chosen from: generative models, feature representation learning, computer vision.
- Prerequisites: (MATH 236 or MATH 247 or MATH 251) and (MATH 248 or MATH 314 or MATH 358) and (COMP 202 or equivalent or permission of the instructor).
- Restriction: Not open to students who have taken or are taking COMP 451 or COMP 551.