November 29, 2021 to December 3, 2021
Virtual and IBS Science Culture Center, Daejeon, South Korea
Asia/Seoul timezone

Understanding Machine Learning via Exactly Solvable Statistical Physics Models

contribution ID 794
Dec 1, 2021, 4:30 PM
30m
Auditorium (Virtual and IBS Science Culture Center, Daejeon, South Korea)

Auditorium

Virtual and IBS Science Culture Center, Daejeon, South Korea

55 EXPO-ro Yuseong-gu Daejeon, South Korea email: library@ibs.re.kr +82 42 878 8299

Speaker

Lenka Zdeborova

Description

The affinity between statistical physics and machine learning has a long history, I will describe the main lines of this long-lasting friendship in the context of current theoretical challenges and open questions about deep learning. Theoretical physics often proceeds in terms of solvable synthetic models, I will describe the related line of work on solvable models of simple feed-forward neural networks. I will highlight a path forward to capture the subtle interplay between the structure of the data, the architecture of the network, and the learning algorithm.

Presentation materials