Instructor:
Peizhong Ju
660
Credits:
3.0
001
Building:
King Library
Room:
Rm.0213E
Semester:
Fall 2024
Start Date:
End Date:
Name:
Tp In Ai: Generative Machine Learning
Requisites:
Prereq: CS 505 and CS 560 or consent of instructor.
Class Type:
LEC
2:00 pm
2:50 pm
Days:
MWF
Note:
This course delves into the rapidly evolving field of generative machine learning, focusing on advanced algorithms and techniques that enable machines to create new data samples from learned patterns. Students will explore various generative models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and other state-of-the-art approaches such as Diffusion Models. The curriculum will cover theoretical foundations, practical implementations, and applications in areas such as image synthesis and natural language processing. Students will gain a comprehensive understanding of how generative models work and how they can be applied. This course emphasizes both the mathematical concepts and the programming skills necessary to develop and evaluate generative models. Prerequisites: Strong programming ability (CS 315), basic probability and statistics (STA 281), and basic concepts of linear algebra (MA/CS 321 or MA/CS 322), or instructor's consent.
Advanced topics chosen from the following: knowledge representation, knowledge acquisition, problem solving, very high-level programming languages, expert systems, intelligent and deductive databases, automated theorem proving. May be repeated to a maximum of six credits, but only three credits may be earned under the same topic.
Advanced topics chosen from the following: knowledge representation, knowledge acquisition, problem solving, very high-level programming languages, expert systems, intelligent and deductive databases, automated theorem proving. May be repeated to a maximum of six credits, but only three credits may be earned under the same topic.
CS