Events

Events at Physics

<< Fall 2021 Spring 2022 Summer 2022 >>
Subscribe your calendar or receive email announcements of events
Physics ∩ ML Seminar
Effective Theory of Deep Neural Networks
Date: Wednesday, April 20th
Time: 11:00 am - 12:15 pm
Place: Online Seminar: Please sign up for our mailing list at www.physicsmeetsml.org for zoom link. We will also livestream the talk in Chamberlin 5280.
Speaker: Sho Yaida, Meta AI
Abstract: Large neural networks perform extremely well in practice, providing the backbone of modern machine learning. The goal of this talk is to provide a blueprint for theoretically analyzing these large models from first principles. In particular, we’ll overview how the statistics and dynamics of deep neural networks drastically simplify at large width and become analytically tractable. In so doing, we’ll see that the idealized infinite-width limit is too simple to capture several important aspects of deep learning such as representation learning. To address them, we’ll step beyond the idealized limit and systematically incorporate finite-width corrections.
Add this event to your calendar