Cargando…
Recurrent connections facilitate symmetry perception in deep networks
Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Yet, the neural underpinnings of symmetry perception remain elusive, as they require abstraction of long-range spatial depen...
Autores principales: | Sundaram, Shobhita, Sinha, Darius, Groth, Matthew, Sasaki, Tomotake, Boix, Xavier |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9719566/ https://www.ncbi.nlm.nih.gov/pubmed/36463378 http://dx.doi.org/10.1038/s41598-022-25219-w |
Ejemplares similares
-
The Data Efficiency of Deep Learning Is Degraded by Unnecessary Input Dimensions
por: D'Amario, Vanessa, et al.
Publicado: (2022) -
Symmetry perception with spiking neural networks
por: George, Jonathan K., et al.
Publicado: (2021) -
Incorporating intrinsic suppression in deep neural networks captures dynamics of adaptation in neurophysiology and perception
por: Vinken, K., et al.
Publicado: (2020) -
Measuring Symmetry, Asymmetry and Randomness in Neural Network Connectivity
por: Esposito, Umberto, et al.
Publicado: (2014) -
The Concept of Symmetry and the Theory of Perception
por: Pizlo, Zygmunt, et al.
Publicado: (2021)