Increasing neural network robustness improves match to macaque V1 eigenspectrum, spatial frequency preference and predictivity

Task-optimized convolutional neural networks (CNNs) show striking similarities to the ventral visual stream. However, human-imperceptible image perturbations can cause a CNN to make incorrect predictions. Here we provide insight into this brittleness by investigating the representations of models th...

Descripción completa

Detalles Bibliográficos
Autores principales: Kong, Nathan C. L., Margalit, Eshed, Gardner, Justin L., Norcia, Anthony M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8775238/
https://www.ncbi.nlm.nih.gov/pubmed/34995280
http://dx.doi.org/10.1371/journal.pcbi.1009739

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8775238/
https://www.ncbi.nlm.nih.gov/pubmed/34995280
http://dx.doi.org/10.1371/journal.pcbi.1009739

Ejemplares similares