Spring 2017

Resilient Representation and Provable Generalization

Friday, Mar. 31, 2017 2:15 pm2:55 pm PDT

Add to Calendar

In this talk, I'll present the challenges in today's deep learning approach for learning representations resilient against attacks. I will also explore the question of providing provable guarantees of generalization of a learned model. As a concrete example, I will present our recent work on using recursion to enable provablely perfect generalization in the domain of neural program architectures.