# A Novel Convolutional Neural Network Architecture with a Continuous Symmetry

Source: [A Novel Convolutional Neural Network Architecture with a Continuous Symmetry](<https://www.sota2.com/research/paper/68fa73451e209131cea5b760>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:46:17.278Z

Authors: Yao Liu, Hang Shao, Bing Bai

Published: 2023-08-03T08:50:48.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.01621>)

[PDF](<https://arxiv.org/pdf/2308.01621.pdf>)