CS Colloquium: Jimmy Ba (University of Toronto) - Progress and Challenges in Training Neural Networks
Thu, Nov 09, 2017 @ 03:30 PM - 04:50 PM
Conferences, Lectures, & Seminars
Speaker: Jimmy Ba, University of Toronto
Talk Title: Progress and Challenges in Training Neural Networks
Series: Visa Research Machine Learning Seminar Series hosted by USC Machine Learning Center
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Optimization lies at the core of any deep learning systems. In this talk, I will first discuss the recent advances in optimization algorithms to train deep learning models. Then I will present a novel family of 2nd-order optimization algorithms that leverage distributed computing to significantly shortening the training time of neural networks with tens of millions of parameters. The talk will conclude by showing how our algorithms can be successfully applied to domains such as reinforcement learning and generative adversarial networks.
Biography: Jimmy is finishing his PhD with Geoff Hinton in the Machine Learning group at the University of Toronto. Jimmy will be a Computational Fellow at MIT before returning as full-time faculty to the CS department at UofT, as well as joining the Vector Institute. Jimmy completed his BAc, MSc at UofT working with Brendan Frey and Ruslan Salakhutdinov. He has previously spent time at Google Deepmind and Microsoft Research, and is a recipient of Facebook Graduate Fellowship for 2016 in machine learning. His primary research interests are in the areas of artificial intelligence, neural networks, and numerical optimization.
Host: Yan Liu
Audiences: Everyone Is Invited
Contact: Computer Science Department