Applied Math Seminar

Date: 
10/24/2019 - 11:00am to 12:00pm
Location: 
POT 745
Speaker(s) / Presenter(s): 
Vasily Zadorozhnyy, University of Kentucky
Title: Generative Adversarial Networks
 
Abstract: ​In 2014, Ian Goodfellow et al. proposed a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. In this talk, I will talk about the structure of such a framework, how we train it as well as some theoretical results and applications.
Tags/Keywords:
Type of Event (for grouping events):
X
Enter your linkblue username.
Enter your linkblue password.
Secure Login

This login is SSL protected

Loading