1

Topographic DCNNs trained on a single self-supervised task capture the functional organization of cortex into visual processing streams
A model trained with a spatial constraint, on a single self-supervised task, can recapitulate the functional organization of visual cortex into multiple processing streams.
Dawn Finzi, Eshed Margalit, Daniel L. K. Yamins, Kendrick Kay, Kalanit Grill-Spector
Cite Source Document
Do deep convolutional neural networks accurately model representations beyond the ventral stream?
While primate visual cortex has typically been divided into two processing streams, recent research suggests that there may be at least …
Dawn Finzi, Daniel L. K. Yamins, Kendrick Kay, Kalanit Grill-Spector
PDF DOI