Emergence of simple-cell receptive field properties by learning a sparse code for natural images

Abstract

THE receptive fields of simple cells in mammalian primary visual cortex can be characterized as being spatially localized, oriented^1–4 and bandpass (selective to structure at different spatial scales), comparable to the basis functions of wavelet transforms^5,6. One approach to understanding such response properties of visual neurons has been to consider their relationship to the statistical structure of natural images in terms of efficient coding^7–12. Along these lines, a number of studies have attempted to train unsupervised learning algorithms on natural images in the hope of developing receptive fields with similar properties^13–18, but none has succeeded in producing a full set that spans the image space and contains all three of the above properties. Here we investigate the proposal^8,12 that a coding strategy that maximizes sparseness is sufficient to account for these properties. We show that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex. The resulting sparse image code provides a more efficient representation for later stages of processing because it possesses a higher degree of statistical independence among its outputs.