Cargando…
Separability and geometry of object manifolds in deep neural networks
Stimuli are represented in the brain by the collective population responses of sensory neurons, and an object presented under varying conditions gives rise to a collection of neural population responses called an ‘object manifold’. Changes in the object representation along a hierarchical sensory sy...
Autores principales: | Cohen, Uri, Chung, SueYeon, Lee, Daniel D., Sompolinsky, Haim |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7005295/ https://www.ncbi.nlm.nih.gov/pubmed/32029727 http://dx.doi.org/10.1038/s41467-020-14578-5 |
Ejemplares similares
-
Neural population geometry: An approach for understanding biological and artificial neural networks
por: Chung, SueYeon, et al.
Publicado: (2021) -
Neural representational geometry underlies few-shot concept learning
por: Sorscher, Ben, et al.
Publicado: (2022) -
Coherent chaos in a recurrent neural network with structured connectivity
por: Landau, Itamar Daniel, et al.
Publicado: (2018) -
Geometry of manifolds
por: Bishop, Richard L, et al.
Publicado: (2001) -
Geometry of manifolds
por: Bishop, Richard, L, et al.
Publicado: (1964)