Cargando…
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...
Autores principales: | Spoerer, Courtney J., Kietzmann, Tim C., Mehrer, Johannes, Charest, Ian, Kriegeskorte, Nikolaus |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7556458/ https://www.ncbi.nlm.nih.gov/pubmed/33006992 http://dx.doi.org/10.1371/journal.pcbi.1008215 |
Ejemplares similares
-
Individual differences among deep neural network models
por: Mehrer, Johannes, et al.
Publicado: (2020) -
An ecologically motivated image dataset for deep learning yields better models of human vision
por: Mehrer, Johannes, et al.
Publicado: (2021) -
Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition
por: Spoerer, Courtney J., et al.
Publicado: (2017) -
Corrigendum: Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition
por: Spoerer, Courtney J., et al.
Publicado: (2018) -
Recurrence is required to capture the representational dynamics of the human visual system
por: Kietzmann, Tim C., et al.
Publicado: (2019)