Events at Physics

<< Fall 2021 Spring 2022 Summer 2022 >>
Subscribe your calendar or receive email announcements of events
Physics ∩ ML Seminar
A duality connecting neural network and cosmological dynamics
Date: Wednesday, April 13th
Time: 11:00 am - 12:15 pm
Place: Chamberlin 5280 (Zoom link also available for online participants who signed up on our mailing list)
Speaker: Sven Krippendorf, Ludwig Maximilian University
Abstract: We demonstrate that the dynamics of neural networks trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly related. This duality provides the framework for synergies between these systems, to understand and explain neural network dynamics and new ways of simulating and describing early Universe models. Working in the continuous-time limit of neural networks, we analytically match the dynamics of the mean background and the dynamics of small perturbations around the mean field, highlighting potential differences in separate limits. We perform empirical tests of this analytic description and quantitatively show the dependence of the effective field theory parameters on hyperparameters of the neural network. As a result of this duality, the cosmological constant is matched inversely to the learning rate in the gradient descent update.
Add this event to your calendar