A course on the fundamentals of machine learning, including basic models, formulations, and modern methods. Topics include PAC learnability, validation, classification, regression, clustering, component analysis, and graphical and deep learning models. Students are expected to have the following background: (i) working knowledge of probability theory and statistics, (ii) working knowledge of linear algebra and algorithms, and (iii) working knowledge of basic computer science principles at a level sufficient to write non-trivial computer programs in a language of preference.
Prerequisite
Limited to CSE graduate students; others, permission of instructor
Credits
3 Credits, Letter graded
Course Outcomes
At the end of the course, students should be able to
describe, explain and dierentiate modern machine learning techniques;
apply existing models and algorithms;
identify potential applications;
select appropriate techniques based on the particular characteristics of the domains and applications under consideration;
evaluate and assess the performance of machine learning algorithms properly.