English

A Geometric Framework for Convolutional Neural Networks

Machine Learning 2016-10-06 v2 Artificial Intelligence Neural and Evolutionary Computing

Abstract

In this paper, a geometric framework for neural networks is proposed. This framework uses the inner product space structure underlying the parameter set to perform gradient descent not in a component-based form, but in a coordinate-free manner. Convolutional neural networks are described in this framework in a compact form, with the gradients of standard --- and higher-order --- loss functions calculated for each layer of the network. This approach can be applied to other network structures and provides a basis on which to create new networks.

Keywords

Cite

@article{arxiv.1608.04374,
  title  = {A Geometric Framework for Convolutional Neural Networks},
  author = {Anthony L. Caterini and Dong Eui Chang},
  journal= {arXiv preprint arXiv:1608.04374},
  year   = {2016}
}

Comments

Added proofs and algorithms that were missing from previous version

R2 v1 2026-06-22T15:20:16.235Z