A Novel Convolutional Neural Network Architecture with a Continuous Symmetry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yao, Shao, Hang, Bai, Bing
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914801240768512
author Liu, Yao
Shao, Hang
Bai, Bing
author_facet Liu, Yao
Shao, Hang
Bai, Bing
contents This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification task, it allows for the modification of the weights via a continuous group of symmetry. This is a significant shift from traditional models where the architecture and weights are essentially fixed. We wish to promote the (internal) symmetry as a new desirable property for a neural network, and to draw attention to the PDE perspective in analyzing and interpreting ConvNets in the broader Deep Learning community.
format Preprint
id arxiv_https___arxiv_org_abs_2308_01621
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
Liu, Yao
Shao, Hang
Bai, Bing
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification task, it allows for the modification of the weights via a continuous group of symmetry. This is a significant shift from traditional models where the architecture and weights are essentially fixed. We wish to promote the (internal) symmetry as a new desirable property for a neural network, and to draw attention to the PDE perspective in analyzing and interpreting ConvNets in the broader Deep Learning community.
title A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
topic Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2308.01621