Neural network models of the tactile system develop first-order units with spatially complex receptive fields

First-order tactile neurons have spatially complex receptive fields. Here we use machine-learning tools to show that such complexity arises for a wide range of training sets and network architectures. Moreover, we demonstrate that this complexity benefits network performance, especially on more diff...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Charlie W., Daley, Mark J., Pruszynski, J. Andrew
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2018
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6002100/
https://www.ncbi.nlm.nih.gov/pubmed/29902277
http://dx.doi.org/10.1371/journal.pone.0199196

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6002100/
https://www.ncbi.nlm.nih.gov/pubmed/29902277
http://dx.doi.org/10.1371/journal.pone.0199196

Ejemplares similares