Cargando…
Emerged human-like facial expression representation in a deep convolutional neural network
Recent studies found that the deep convolutional neural networks (DCNNs) trained to recognize facial identities spontaneously learned features that support facial expression recognition, and vice versa. Here, we showed that the self-emerged expression-selective units in a VGG-Face trained for facial...
Autores principales: | Zhou, Liqin, Yang, Anmin, Meng, Ming, Zhou, Ke |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Association for the Advancement of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8942361/ https://www.ncbi.nlm.nih.gov/pubmed/35319988 http://dx.doi.org/10.1126/sciadv.abj4383 |
Ejemplares similares
-
Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces
por: Song, Yiying, et al.
Publicado: (2021) -
Non-uniqueness Phenomenon of Object Representation in Modeling IT Cortex by Deep Convolutional Neural Network (DCNN)
por: Dong, Qiulei, et al.
Publicado: (2020) -
Multidimensional Face Representation in a Deep Convolutional Neural Network Reveals the Mechanism Underlying AI Racism
por: Tian, Jinhua, et al.
Publicado: (2021) -
Semantic Relatedness Emerges in Deep Convolutional Neural Networks Designed for Object Recognition
por: Huang, Taicheng, et al.
Publicado: (2021) -
Representational Distance Learning for Deep Neural Networks
por: McClure, Patrick, et al.
Publicado: (2016)