A Novel Convolutional Neural Network Architecture with a Continuous Symmetry

Code

• github.com/liuyao12/ConvNets-PDE-perspective
  Officialpytorch★ 21

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.

Tasks

Reproductions