HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Hyvärinen, A. Articles by Hoyer, P. Search for Related Content PubMed PubMed Citation Articles by Hyvärinen, A. Articles by Hoyer, P.

Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Helsinki University of Technology, Laboratory of Computer and Information Science, FIN-02015 HUT, Finland

Patrik Hoyer

Helsinki University of Technology, Laboratory of Computer and Information Science, FIN-02015 HUT, Finland

Olshausen and Field (1996) applied the principle of independence maximization by sparse coding to extract features from natural images. This leads to the emergence of oriented linear filters that have simultaneous localization in space and in frequency, thus resembling Gabor functions and simple cell receptive fields. In this article, we show that the same principle of independence maximization can explain the emergence of phase- and shift-invariant features, similar to those found in complex cells. This new kind of emergence is obtained by maximizing the independence between norms of projections on linear subspaces (instead of the independence of simple linear filter outputs). The norms of the projections on such "independent feature subspaces" then indicate the values of invariant features.

This article has been cited by other articles:

				M. O. Franz and B. Scholkopf A unifying view of wiener and volterra theory and polynomial kernel regression. Neural Comput., December 1, 2006; 18(12): 3097 - 3118. [Abstract] [Full Text] [PDF]

				O. Schwartz, T. J. Sejnowski, and P. Dayan Soft mixer assignment in a hierarchical generative model of natural scene statistics. Neural Comput., November 1, 2006; 18(11): 2680 - 2718. [Abstract] [Full Text] [PDF]

				P. Berkes and L. Wiskott On the Analysis and Interpretation of Inhomogeneous Quadratic Forms as Receptive Fields Neural Comput., August 1, 2006; 18(8): 1868 - 1895. [Abstract] [Full Text] [PDF]

				Y. Matsuda and K. Yamaguchi Linear Multilayer ICA Generating Hierarchical Edge Detectors Neural Comput., January 1, 2006; 19(1): 218 - 230. [Abstract] [Full Text] [PDF]

				K. N. O'Connor, C. I. Petkov, and M. L. Sutter Adaptive Stimulus Optimization for Auditory Cortical Neurons J Neurophysiol, December 1, 2005; 94(6): 4051 - 4067. [Abstract] [Full Text] [PDF]

				Y. Karklin and M. S. Lewicki A Hierarchical Bayesian Model for Learning Nonlinear Statistical Regularities in Nonstationary Natural Signals Neural Comput., February 1, 2005; 17(2): 397 - 423. [Abstract] [Full Text] [PDF]

				K. Zhang and L.-W. Chan An Adaptive Method for Subband Decomposition ICA Neural Comput., January 1, 2005; 18(1): 191 - 223. [Abstract] [Full Text] [PDF]

				K. P. Kording, C. Kayser, W. Einhauser, and P. Konig How Are Complex Cell Properties Adapted to the Statistics of Natural Stimuli? J Neurophysiol, January 1, 2004; 91(1): 206 - 212. [Abstract] [Full Text]

				A. Hyvarinen, P. O. Hoyer, and M. Inki Topographic Independent Component Analysis Neural Comput., July 1, 2001; 13(7): 1527 - 1558. [Abstract] [Full Text]