A Novel Convolutional Neural Network Architecture with a Continuous Symmetry
This work proposes a new property for neural networks, promoting symmetry and PDE perspectives, which could influence the broader Deep Learning community.
The paper tackles the problem of rigid neural network architectures by introducing a ConvNet with continuous symmetry, enabling weight modification without performance loss, achieving comparable accuracy on image classification tasks.
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.