Saved in:
Bibliographic Details
Main Authors: Bao, Erkao, Lu, Jingcheng, Song, Linqi, Hart-Hodgson, Nathan, Parson, William, Zhou, Yanheng
Format: Preprint
Published: 2019
Subjects:
Online Access:https://arxiv.org/abs/1906.07172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917086736941056
author Bao, Erkao
Lu, Jingcheng
Song, Linqi
Hart-Hodgson, Nathan
Parson, William
Zhou, Yanheng
author_facet Bao, Erkao
Lu, Jingcheng
Song, Linqi
Hart-Hodgson, Nathan
Parson, William
Zhou, Yanheng
contents Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_1906_07172
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Equivariant neural networks and equivarification
Bao, Erkao
Lu, Jingcheng
Song, Linqi
Hart-Hodgson, Nathan
Parson, William
Zhou, Yanheng
Machine Learning
Computer Vision and Pattern Recognition
Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.
title Equivariant neural networks and equivarification
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1906.07172