| Título |
Optimizing the Simplicial-Map Neural Network Architecture |
| Autores |
PALUZO HIDALGO, EDUARDO, Gonzalez-Diaz, Rocio , Gutierrez-Naranjo, Miguel A. , Heras, Jonathan |
| Publicación externa |
Si |
| Medio |
Journal of Imaging |
| Alcance |
Article |
| Naturaleza |
Científica |
| Cuartil SJR |
2 |
| Impacto SJR |
0.728 |
| Fecha de publicacion |
01/09/2021 |
| ISI |
000699599700001 |
| DOI |
10.3390/jimaging7090173 |
| Abstract |
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. |
| Palabras clave |
simplicial-map neural networks; artificial neural networks; computational topology |
| Miembros de la Universidad Loyola |
|
Gestionar cookies