27–31 May 2024
ECT*
Europe/Rome timezone

Effective Theory of Deep Neural Networks

30 May 2024, 09:30
45m
Aula Renzo Leonardi (ECT*)

Aula Renzo Leonardi

ECT*

Strada delle Tabarelle 286, I-38123 Villazzano (Trento)

Speaker

Sho Yaida (Meta Platforms, Inc.)

Description

Large neural networks perform extremely well in practice, providing the backbone of modern machine learning. In this talk, we'll first overview how the statistics and dynamics of deep neural networks drastically simplify at large width and become analytically tractable. We'll then see how the concepts of the renormalization-group flow and critical phenomena naturally emerge in computing and controlling various observables that govern the behavior of deep neural networks.

Primary author

Sho Yaida (Meta Platforms, Inc.)

Presentation materials