Layerwise complexity-matched learning yields an improved model of cortical area V2

arXiv:2312.11436v2 Announce Type: replace-cross
Abstract: Human ability to recognize complex visual patterns arises through transformations performed by successive areas in the ventral visual cortex. Deep neural networks trained end-to-end for object recognition approach human capabilities, and offer the best descriptions to date of neural responses in the late stages of the hierarchy. But these networks provide a poor account of the early stages, compared to traditional hand-engineered models, or models optimized for coding efficiency or prediction. Moreover, the gradient backpropagation …

abstract arxiv capabilities complexity cortex cs.cv cs.lg human networks neural networks patterns q-bio.nc recognition responses through type visual visual cortex