Grounding deep neural network predictions of human categorization behavior in understandable functional features: The case of face identity

Deep neural networks (DNNs) can resolve real-world categorization tasks with apparent human-level performance. However, true equivalence of behavioral performance between humans and their DNN models requires that their internal mechanisms process equivalent features of the stimulus. To develop such...

Descripción completa

Detalles Bibliográficos
Autores principales: Daube, Christoph, Xu, Tian, Zhan, Jiayu, Webb, Andrew, Ince, Robin A.A., Garrod, Oliver G.B., Schyns, Philippe G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8515012/
https://www.ncbi.nlm.nih.gov/pubmed/34693374
http://dx.doi.org/10.1016/j.patter.2021.100348

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8515012/
https://www.ncbi.nlm.nih.gov/pubmed/34693374
http://dx.doi.org/10.1016/j.patter.2021.100348

Ejemplares similares