Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision.
Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computational resources over time, and so might boost the...
Сохранить в:
| Главные авторы: | , , , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
Public Library of Science (PLoS)
2020-10-01
|
| Серии: | PLoS Computational Biology |
| Online-ссылка: | https://doi.org/10.1371/journal.pcbi.1008215 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|