Mean Field Approaches to Learning Dynamics in Deep Networks
Video · 41 min · Nov 29, 2023
Blake Bordelon, Harvard University
Wilsonian Renormalization of Neural Network Field Theories
Deep Learning, Machine Learning, Theoretical Physics and seminar by Zohar Ringel, Hebrew University of Jerusalem
Tuesday 15:30–17:00 Toronto (GMT-4)
Ended
Waterloo, Canada
Abstract
Zohar Ringel of the Hebrew University of Jerusalem presents a renormalisation-group approach to deep learning based on neural-network field theories. The seminar examines scaling laws, the removal of non-learnable field modes, benign overfitting and open questions about feature learning. The confirmed Quantum Matter seminar takes place in the Bob Room at Perimeter Institute on 8 September 2026, from 15:30 to 17:00 Toronto time.
Topics
renormalisationscaling laws
Related seminars
Matrix Factorization with Neural Networks
Video · 45 min · Jan 3, 2024Marc Mézard, Bocconi University, MilanoA function approximation perspective on neural representations
Video · 59 min · Dec 2, 2020Cengiz Pehlevan, Harvard University
More from Perimeter Institute for Theoretical Physics
All talksBig Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI
Oct 7, 2026Zohar RingelReshaping Metrology with Quantum Information Processing
Video · 1 h 25 min · Sep 30, 2026Sisi ZhouHow dark matter halos get their cusps
Video · 1 h 5 min · Sep 29, 2026Uddipan BanikEmergent time and more from wavefunction collapse in general relativity
Sep 24, 2026Sung-Sik Lee