# Rigorous results from Machine Learning for Theoretical Physics

Rigorous results from Machine Learning for Theoretical Physics

Fabian Ruehle, Northeastern University

Date and time:
Tue, Feb 20, 2024 - 2:30pm

Location:
LGRT 1033

Category:
ACFI Seminar

Speaker link:
Fabian Ruehle's Home Page

Abstract:

Machine learning techniques are increasingly powerful, but they are also often black-box and make stochastic rather than exact predictions, making them less attractive for theoretical physicists and mathematicians. In this talk, I summarize recent ideas and developments to overcome this problem.

I will start with a short introduction to neural networks, which form the backbone of modern machine learning applications, and subsequently introduce a field of machine learning called reinforcement learning. Using examples from physics and mathematics, I will illustrate how ML techniques can be used to generate (and hopefully subsequently prove) new conjectures, and to obtain rigorous, verifiably correct results.

## Department of Physics

Find us on FacebookSubscribe to us on YouTubeConnect with us on LinkedIn