University of Cambridge > Talks.cam > Applied and Computational Analysis > Physics-Enhanced Machine Learning (with sampling)

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Physics-Enhanced Machine Learning (with sampling)

Download to your calendar using vCal

If you have a question about this talk, please contact Matthew Colbrook .

I will present the recent work done by Felix Deitrich’s group in Munich. The talk will specifically focus on the SWIM method [1], a sampling algorithm that allows fast and accurate construction of neural network weights. I will cover the basic SWIM method and its recent developments: SWIM -PDE to solve partial differential equations [2] and SWIM -RNN to learn dynamical systems with a combination of neural networks and the Koopman operator.

[1] Bolager, E.L., IB, Datar, C., Sun, Q. and Dietrich, F., 2024. Sampling weights of deep neural networks. Advances in Neural Information Processing Systems, 36. [2] Datar, C., Kapoor, T., Chandra, A., Sun, Q., IB, Bolager, E.L., Veselovska, A., Fornasier, M. and Dietrich, F., 2024. Solving partial differential equations with sampled neural networks. arXiv preprint arXiv:2405.20836.

This talk is part of the Applied and Computational Analysis series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

DELPH-IN Summit Open Session Authur Marshall Room Gonville & Caius College, Cambridge: the Green Room

Other talks

A Novel Diffusion Model based Approach for Sleep Music Generation title abstract tbc Title to be confirmed Welcome Reception and Poster Session John Kendrew Lecture - Title TBC Am I a Member? Auditing Private Machine Learning
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity