AI summary

This paper proposes a learning algorithm for natural image sparse coding that produces simple-cell receptive fields with localized, oriented, and bandpass properties, similar to those found in primary visual cortex, achieving a more efficient representation through increased statistical independence.

Abstract

THE receptive fields of simple cells in mammalian primary visual cortex can be characterized as being spatially localized, oriented and bandpass (selective to structure at different spatial scales), comparable to the basis functions of wavelet transforms. One approach to understanding such response properties of visual neurons has been to consider their relation- ship to the statistical structure of natural images in terms of efficient coding. 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, 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 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 recep- tive fields, similar to those found in the primary visual cortex. The resulting sparse image code provides a more efficient representa- tion for later stages of processing because it possesses a higher degree of statistical independence among its outputs.