Timezone: »

 
Poster
Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Risi Kondor · Zhen Lin · Shubhendu Trivedi

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #130
in Tue Poster Session A »

Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory and noncommutative harmonic analysis. In this paper we propose a generalization of this work that generally exhibits improved performace, but from an implementation point of view is actually simpler. An unusual feature of the proposed architecture is that it uses the Clebsch--Gordan transform as its only source of nonlinearity, thus avoiding repeated forward and backward Fourier transforms. The underlying ideas of the paper generalize to constructing neural networks that are invariant to the action of other compact groups.

Keywords: Deep Learning · Supervised Deep Networks · Efficient Training Methods · CNN Architectures
[ Paper] 

Author Information

Risi Kondor (U. Chicago)

Risi Kondor joined the Flatiron Institute in 2019 as a Senior Research Scientist with the Center for Computational Mathematics. Previously, Kondor was an Associate Professor in the Department of Computer Science, Statistics, and the Computational and Applied Mathematics Initiative at the University of Chicago. His research interests include computational harmonic analysis and machine learning. Kondor holds a Ph.D. in Computer Science from Columbia University, an MS in Knowledge Discovery and Data Mining from Carnegie Mellon University, and a BA in Mathematics from the University of Cambridge. He also holds a diploma in Computational Fluid Dynamics from the Von Karman Institute for Fluid Dynamics and a diploma in Physics from Eötvös Loránd University in Budapest.

Zhen Lin (The University of Chicago)
Shubhendu Trivedi (Brown University)

More from the Same Authors