Posted September 26, 2024
Applied Analysis Seminar Questions or comments?
3:30 pm Lockett 232
Matias Delgadino, University of Texas at Austin
Generative Adversarial Networks: Dynamics
Generative Adversarial Networks (GANs) was one of the first Machine Learning algorithms to be able to generate remarkably realistic synthetic images. In this presentation, we delve into the mechanics of the GAN algorithm and its profound relationship with optimal transport theory. Through a detailed exploration, we illuminate how GAN approximates a system of PDE, particularly evident in shallow network architectures. Furthermore, we investigate known pathological behaviors such as mode collapse and failure to converge, and elucidate their connections to the underlying PDE framework through an illustrative example.
Posted September 11, 2024
Applied Analysis Seminar Questions or comments?
3:30 pm Lockett 232
Michael Novack, Louisiana State University
TBA