Optimizing the Simplicial-Map Neural Network Architecture

Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper,...

Full description

Saved in:
Bibliographic Details
Published inJournal of imaging Vol. 7; no. 9; p. 173
Main Authors Paluzo-Hidalgo, Eduardo, Gonzalez-Diaz, Rocio, Gutiérrez-Naranjo, Miguel A, Heras, Jónathan
Format Journal Article
LanguageEnglish
Published Switzerland MDPI AG 01.09.2021
MDPI
Subjects
artificial neural networks
Classification
computational topology
Computer architecture
Datasets
Deep learning
Neural networks
Regularization methods
simplicial-map neural networks
Support vector machines
simplicial-map neural networks
artificial neural networks
computational topology
Online AccessGet full text

Cover

More Information
Summary:Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper, the refinement toward robustness is optimized by reducing the number of simplices (i.e., nodes) needed. We have shown experimentally that such a refined neural network is equivalent to the original network as a classification tool but requires much less storage.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2313-433X
2313-433X
DOI:10.3390/jimaging7090173