Clustering Inductive Biases with Unrolled Networks

arXiv:2402.10213v1 Announce Type: cross
Abstract: The classical sparse coding (SC) model represents visual stimuli as a linear combination of a handful of learned basis functions that are Gabor-like when trained on natural image data. However, the Gabor-like filters learned by classical sparse coding far overpredict well-tuned simple cell receptive field profiles observed empirically. While neurons fire sparsely, neuronal populations are also organized in physical space by their sensitivity to certain features. In V1, this organization is a smooth progression of …

abstract arxiv biases clustering coding combination cs.ai cs.lg data filters functions image image data inductive linear natural networks profiles q-bio.nc simple type visual