Introduction to Equivariant Machine Learning - IPAM at UCLA

Overview

Explore the fundamentals of equivariant machine learning in this 46-minute lecture presented by Soledad Villar from Johns Hopkins University at IPAM's Mathematical Advances for Multi-Dimensional Microscopy Workshop. Delve into the concept of machine learning models that respect the fundamental symmetries of physical descriptions. Gain insights into the implementation of these models and understand their significance in the field. Recorded on October 27, 2022, at the Institute for Pure & Applied Mathematics (IPAM) at UCLA, this talk provides a comprehensive introduction to the principles and applications of equivariant machine learning.

Syllabus

Soledad Villar - Introduction to equivariant machine learning - IPAM at UCLA

Taught by

Institute for Pure & Applied Mathematics (IPAM)

Reviews

Start your review of Introduction to Equivariant Machine Learning - IPAM at UCLA

Taught by

Equivariant Machine Learning Structured Like Classical Physics

Machine Learning with Python: A Practical Introduction

Introduction to Machine Learning with Python

Equivariant Machine Learning from Classical Physics

Machine Learning Introduction for Everyone

The Passive Symmetries of Machine Learning

Never Stop Learning.