Tue, Sep 05, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ian Goodfellow, Google
Talk Title: Generative Adversarial Networks
Series: NVIDIA Distinguished Lecture Series in Machine Learning
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
Generative adversarial networks (GANs) are machine learning models that are able to imagine new data, such as images, given a set of training data. They solve difficult approximate probabilistic computations using game theory. A generator network competes to fool a discriminator network in a game whose Nash equilibrium corresponds to recovering the probability distribution that generated the training data. GANs open many possibilities for machine learning algorithms.
Rather than associating input values in the training set with specific output values, GANs are able to learn to evaluate whether a particular output was one of many potential acceptable outputs or not.
Part of NVIDIA Distinguished Lecture Series in Machine Learning.
Biography: Ian Goodfellow (PhD in machine learning, University of Montreal, 2014) is a research scientist at Google. His research interests include most deep learning topics, especially generative models and machine learning security and privacy. He invented generative adversarial networks, was an influential early researcher studying adversarial examples, and is the lead author of the MIT Press textbook Deep Learning (www.deeplearningbook.org). He runs the Self-Organizing Conference on Machine Learning, which was founded at OpenAI in 2016.
Host: Yan Liu
Audiences: Everyone Is Invited
Contact: Computer Science Department