Seminar, Hosted by Perimeter Institute for Theoretical Physics

Wilsonian Renormalization of Neural Network Field Theories

Hebrew University of Jerusalem

Deep Learning, Machine Learning and

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

renormalisation, search World Wide
scaling laws

Source: events.perimeterinstitute.ca

Wilsonian Renormalization of Neural Network Field Theories

Abstract

Topics

Mean Field Approaches to Learning Dynamics in Deep Networks

Neural Networks and Quantum Mechanics

Matrix Factorization with Neural Networks

Big Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI

Big Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI

Wilsonian Renormalization of Neural Network Field Theories

Abstract

Topics

Related

Mean Field Approaches to Learning Dynamics in Deep Networks

Neural Networks and Quantum Mechanics

Matrix Factorization with Neural Networks

More with Zohar Ringel

Big Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI

Big Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI