TH String Theory Seminar

The Principles of Deep Learning Theory

by Dan Roberts (MIT & Salesforce)

Europe/Zurich
zoom (CERN)

zoom

CERN

Description

Deep learning is an exciting approach to modern artificial intelligence based on artificial neural networks. The goal of this talk is to provide a blueprint — using tools from physics — for theoretically analyzing deep neural networks of practical relevance. This task will encompass both understanding the statistics of initialized deep networks and determining the training dynamics of such an ensemble when learning from data. Borrowing from the "effective theory" framework of physics and developing a perturbative 1/n expansion around the limit of infinite hidden-layer width, we will find a principle of sparsity that will let us describe effectively-deep networks of practical large-but-finite-width networks.

This talk is based on a book, "The Principles of Deep Learning Theory," co-authored with Sho Yaida and based on research also in collaboration with Boris Hanin. It will be published this month by Cambridge University Press.

Videoconference
String Seminars
Zoom Meeting ID
61053603623
Host
Elena Gianolio
Alternative hosts
Shota Komatsu, Kyriakos Papadodimas, Matthew Dodelson, Alexander Zhiboedov, Pascal Pignereau
Passcode
87794299
Useful links
Join via phone
Zoom URL