Volume 410 -
The 5th International Workshop on Deep Learning in Computational Physics (DLCP2021) -
Regular papers
Equivariant Gaussian Processes as Limiting Convolutional Networks with Infinite Number of Channels
Full text:
pdf
Pre-published on:
December 01, 2021
Published on:
January 12, 2022
Abstract
In this work we establish a relationship between the many-channel limit for $SO(2)$-equivariant convolutional neural networks (CNNs) and the corresponding equivariant Gaussian process (GP) in the case of Fourier space quadratic nonlinearity. The approach used provides explicit equivariance at each step of the relationship derivation.
DOI: https://doi.org/10.22323/1.410.0002
How to cite
Metadata are provided both in "article" format (very similar to INSPIRE) as this helps creating very compact bibliographies which can be beneficial to authors and readers, and in "proceeding" format which is more detailed and complete.
Open Access
Copyright owned by the author(s) under the term of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright owned by the author(s) under the term of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.