Explore the intersection of machine learning and modular forms theory in this 23-minute conference talk from GSI. Delve into the concept of SL(2, Z)-equivariant machine learning and its applications, gaining insights into how this mathematical approach can enhance AI models. Learn about the fundamental principles of modular forms and their relevance to equivariant neural networks. Discover potential use cases and practical implementations of this advanced technique in various fields of study and industry applications.
SL(2, Z)-Equivariant Machine Learning with Modular Forms - Theory and Applications
Overview
Syllabus
SL(2, Z)-Equivariant Machine Learning with Modular Forms Theory and Applications
Taught by
Conference GSI
Related Courses
-
Don Zagier: Holomorphic Quantum Modular Forms
-
Equivariant Machine Learning Structured Like Classical Physics
-
Modular Forms and String Theory - Lecture 1
-
Modular Forms and String Theory - Lecture 2
-
Learning How to Break Symmetry With Symmetry-Preserving Neural Networks - IPAM at UCLA
-
Harnessing the Properties of Equivariant Neural Networks for Materials Science
