YoVDO

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

Offered By: Yannic Kilcher via YouTube

Tags

Manifolds Courses Medical Imaging Courses

Course Description

Overview

Explore a video lecture on gauge equivariant convolutional networks and their application to icosahedral CNNs. Delve into the extension of equivariance principles from global symmetries to local gauge transformations, enabling the development of a general class of convolutional neural networks on manifolds. Learn how this approach depends only on intrinsic geometry and encompasses various methods from equivariant and geometric deep learning. Discover the implementation of gauge equivariant CNNs for signals on the icosahedron surface, offering a practical approximation of spherical data. Understand how this method achieves significant improvements in tasks such as segmenting omnidirectional images and global climate patterns, demonstrating its potential as a scalable alternative to Spherical CNNs.

Syllabus

Gauge Equivariant Convolutional Networks and the Icosahedral CNN


Taught by

Yannic Kilcher

Related Courses

Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital
Duke University via Coursera
Statistical Shape Modelling: Computing the Human Anatomy
University of Basel via FutureLearn
Les deux infinis et nous - Voyages de l'infiniment grand à l'infiniment petit
École Polytechnique via Coursera
Life, Health and Radiation
The University of Sydney via Coursera
Toward automatic digital pathology image analysis
Universidad Politécnica de Madrid via Miríadax