Deep Learning for Physics

Organizers: Sanjeev Arora, Curtis Callan, and Victor Mikhaylov “Deep learning” refers to use of neural networks to solve learning problems, including “learning” hidden structures in large and complex data sets. The theory for this field is still in its infancy. Lately physical and biological scientists have begun to explore how it might apply to their domains. This seminar series seeks to introduce the theoretical science community in Princeton and surrounding regions to the practice, promise, and problems of deep learning. It will consist of monthly afternoon sessions ---geared to the broader scientific community--- that will feature an invited talk followed by informal discussions among participants. The schedule will be updated whenever dates for new speakers are confirmed.This seminar series is coordinated with the “Special Year on Optimization, Statistics, and Theoretical Machine Learning” at the Institute for Advanced Study (under the direction of co-organizer Sanjeev Arora).Register here: http://pcts.princeton.edu/programs/current/deep-learning-for-physics-seminar-series/121