Symmetric Simplicial Neural Networks

N. Rodriguez, P. Julian, M. Villemur

Research output: Conference proceeding/Chapter in Book/Report/Conference Paperpeer-review

Abstract

Convolutional Neural Networks are capable of perform many complex tasks such as image classification. Recently morphological functions where introduced as a replacement of the first convolutional layers in any net, using their non-linearities to achieve better accuracy for classification Neural Networks, but in most cases the functions are fixed beforehand and can not be trained. We propose the use of Symmetric Simplicial algorithm that can be trained to perform many morphological computations and even more complex functions. We present the training of a certain topology that uses Symmetric Simplicials instead of morphological functions and the classification accuracy achieved during the training process.
Original languageEnglish
Title of host publication2021 55th Annual Conference on Information Sciences and Systems, CISS 2021
PublisherIEEE Computer Society
Pages1-6
Number of pages6
ISBN (Print)9781665412681
DOIs
Publication statusPublished - 24 Mar 2021
Event2021 55th Annual Conference on Information Sciences and Systems (CISS) - Baltimore, MD, USA
Duration: 24 Mar 202126 Mar 2021

Publication series

Name2021 55th Annual Conference on Information Sciences and Systems, CISS 2021

Conference

Conference2021 55th Annual Conference on Information Sciences and Systems (CISS)
Period24/03/2126/03/21

Keywords

  • Training
  • Neurons
  • Training data
  • Feature extraction
  • Topology
  • Task analysis
  • Biological neural networks
  • PWL
  • Symmetric Simplicial functions
  • Deep Neural Networks
  • Morphological Neural Networks

Fingerprint

Dive into the research topics of 'Symmetric Simplicial Neural Networks'. Together they form a unique fingerprint.

Cite this