CS 3520 Fundamental Machine Learning 3.0 Credits
This course is a breadth survey of traditional supervised and unsupervised machine learning algorithms that lay the groundwork for state-of-the-art techniques. It also introduces core machine learning concepts such as datasets, evaluation, overfitting, regularization and more. The course focuses on the underlying mathematical principles of these algorithms (probability and statistics, gradient-based learning, principal component analysis, etc..) and students get the opportunity to implement various algorithms from scratch, without the use of any frameworks or APIs, in addition to exposure to modern ML APIs.
Repeat Status: Not repeatable for credit
Prerequisites: (CS 1031 [Min Grade: D] or CS 172 [Min Grade: D]) and (CS 2110 [Min Grade: D] or MATH 2402 [Min Grade: D] or CS 260 [Min Grade: D] or MATH 180 [Min Grade: D] or MATH 221 [Min Grade: D]) and (MATH 2401 [Min Grade: D] or MATH 201 [Min Grade: D])