CS Events Monthly View

Qualifying Exam

Disconnected Manifold Learning for Generative Adversarial Networks

 

Download as iCal file

Thursday, September 27, 2018, 11:00am

 

Real images often lie on a union of disjoint manifolds rather than one globally connected manifold, and this can hinder the training of common Generative Adversarial Networks (GANs). We first show that single generator GANs are unable to correctly model

Speaker: Mahyar Khayatkhoei

Bio

NULL

Location : Hill 482

Committee

Prof. Ahmed Elgammal (Chair), Prof. Abdeslam Boularias, Prof. Pranjal Awasthi, Prof. William Steiger

Event Type: Qualifying Exam

Abstract: 

Organization

Dept. of Computer Science