Learning efficient internal representations from natural image collections

Abstract Learning in sensory systems takes place after a repeated exposure to the incoming signals and many ideas based on information theoretical principles have been proposed to explain the synaptic adaptation which improves the coding capabilities of sensory areas. In this paper we want to emphasize that a simple, natural learning rule can be derived from a careful treatment of image redundancies. The learning rule is used to split images into independent components which connect different resolution levels, in a nonlinear way. The result shows the biological plausibility of this coding strategy not only in the visual pathway but also in other sensory modalities.

[1]  A Turiel,et al.  Multifractal wavelet filter of natural images. , 2000, Physical review letters.

[2]  J. H. Hateren,et al.  Theoretical predictions of spatiotemporal receptive fields of fly LMCs, and experimental validation , 1992, Journal of Comparative Physiology A.

[3]  Zhaoping Li,et al.  Towards a theory of striate cortex , 1994 .

[4]  Zhaoping Li,et al.  Toward a Theory of the Striate Cortex , 1994, Neural Computation.

[5]  Néstor Parga,et al.  Role of statistical symmetries in sensory coding: an optimal scale invariant code for vision , 2003, Journal of Physiology-Paris.

[6]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[7]  J. H. Hateren,et al.  Independent component filters of natural images compared with simple cells in primary visual cortex , 1998 .

[8]  J. Nadal,et al.  Nonlinear neurons in the low-noise limit: a factorial code maximizes information transfer Network 5 , 1994 .

[9]  D. Ruderman.  The statistics of natural images , 1994 .

[10]  Antonio Turiel,et al.  Orientational minimal redundancy wavelets: from edge detection to perception , 2003, Vision Research.

[11]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

[12]  J. Nadal,et al.  Self-Similarity Properties of Natural Images Resemble Those of Turbulent Flows , 1998, cond-mat/0107314.

[13]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[14]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Antonio Turiel,et al.  The Multifractal Structure of Contrast Changes in Natural Images: From Sharp Edges to Textures , 2000, Neural Computation.