Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain

Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interf...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Chi, Duan, Xiao-Han, Wang, Lin-Yuan, Li, Yong-Li, Yan, Bin, Hu, Guo-En, Zhang, Ru-Yuan, Tong, Li
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8375771/
https://www.ncbi.nlm.nih.gov/pubmed/34421567
http://dx.doi.org/10.3389/fninf.2021.677925

Ejemplares similares