Cargando…
'Artiphysiology' reveals V4-like shape tuning in a deep network trained for image classification
Deep networks provide a potentially rich interconnection between neuroscientific and artificial approaches to understanding visual intelligence, but the relationship between artificial and neural representations of complex visual form has not been elucidated at the level of single-unit selectivity....
Autores principales: | Pospisil, Dean A, Pasupathy, Anitha, Bair, Wyeth |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
eLife Sciences Publications, Ltd
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6335056/ https://www.ncbi.nlm.nih.gov/pubmed/30570484 http://dx.doi.org/10.7554/eLife.38242 |
Ejemplares similares
-
The unbiased estimation of the fraction of variance explained by a model
por: Pospisil, Dean A., et al.
Publicado: (2021) -
Training Deep Spiking Convolutional Neural Networks With STDP-Based Unsupervised Pre-training Followed by Supervised Fine-Tuning
por: Lee, Chankyu, et al.
Publicado: (2018) -
Detecting shapes in noise: tuning characteristics of global shape mechanisms
por: Schmidtmann, Gunnar, et al.
Publicado: (2013) -
High-density recording reveals sparse clusters (but not columns) for shape and texture encoding in macaque V4
por: Namima, Tomoyuki, et al.
Publicado: (2023) -
Robot Communication: Network Traffic Classification Based on Deep Neural Network
por: Ge, Mengmeng, et al.
Publicado: (2021)