COSC 7362: Advanced Machine Learning, Spring 2023

General Information

Instructor:

Ricardo Vilalta (rvilalta@uh.edu)

Office:

MRE Building, Room 203C.

Office Hours:

By appointment only

Class Time:

Tuesdays and Thursdays 11:30 AM - 1:00 PM (online via MS Teams)

Telephone:

(713) 743-3614

Readings:

TA Information

Michael Meskhi
Office: MRE Building, Room 203B.
Office Hours: Fridays 11:00 AM - Noon
Email: michael.m.meskhi@live.com

Course Description

Welcome to Advanced Machine Learning! The objective of this course is to teach modern topics in machine learning. The course will deepen the student's knowledge of how to build computer systems that learn from experience. The course assumes basic knowledge of introductory machine learning, and a good background on probability and statistics, linear algebra, and optimization methods. We will cover modern topics such as learning theory, transfer learning, meta-learning, domain adaptation, self-adaptive learning algorithms, deep learning, Gaussian processes, and kernel methods. Students will read papers from main conferences in machine learning and will learn to identify novel ideas within the field.

For more information visit the course on Blackboard.

Grading

Graded Work Weight
Quizzes 20%
Presentation 40%
Final Project 40%

Calendar

Dates to Remember Event
January 17 1st class
March 14, 16 No Class; Spring Break
April 11-27 Project Presentations
May 5 Final Project Due

Note: There is no final exam in this course.

Schedule

Dates Topic
January 17, 19 Introduction to Advanced Machine Learning
Meta-Learning
January 24, 26 Self-Adaptive Learning
January 31, February 2 Semi-Supervised Learning
February 7, 9 Transfer Learning
February 14, 16 Domain Adaptation
February 21, 23 Active Learning
February 28, March 2 Kernel Methods
March 7, 9 Gaussian Processes
March 14, 16 No Class, Spring Break
March 21, 23 Deep Learning
March 28, 30 Bayesian Networks
April 4, 6 Special Topic: Information Theory
April 11, 13 Paper Presentations
April 18, 20 Paper Presentations
April 25, 27 Paper Presentations
May 5 Final Project Due

Additional Information

For more information visit the course on Blackboard.