Convergent evolution of face spaces across human face-selective neuronal groups and deep convolutional networks
Deep convolutional neural networks (DCNNs) are able to identify faces on par with humans. Here, the authors record neuronal activity from higher visual areas in humans and show that face-selective responses in the brain show similarity to those in the intermediate layers of the DCNN.
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2019
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/e98fc9d58d49400dacc21b3515cf7cb8 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Deep convolutional neural networks (DCNNs) are able to identify faces on par with humans. Here, the authors record neuronal activity from higher visual areas in humans and show that face-selective responses in the brain show similarity to those in the intermediate layers of the DCNN. |
|---|