Quadratic forms in natural images

Several studies have succeeded in correlating natural image statistics with receptive field properties of neurons in the primary visual cortex. If we determine the parameters of linear transformations that make their output values as independent as possible when input data are natural images, we obtain parameter values that correspond to simple cell characteristics. It was also proved that, by making output values as temporally coherent as possible, simple cell characteristics also emerge. However, complex cell properties have not been fully explained by previous studies of natural image statistics. In this study, we examine whether we could reproduce complex cell properties by determining the parameters of two-layer networks that make their outputs as independent and sparse as possible or as temporally coherent as possible. Input–output functions of two-layer networks correspond to quadratic forms and they form a class of functions that includes complex cell responses and many other functions. Therefore, we employed two-layer networks as a framework for discussing complex cell properties as in previous studies. By maximizing the independence and sparseness of output values of two-layer networks without considering the temporal structure of input images, squared responses of simple cells are obtained and complex cell properties are not reproduced. On the other hand, by maximizing the temporal coherence of output, we obtain complex cell properties among other kinds of input–output functions. In previous studies, the measure of temporal coherence was the squared difference between the responses to two consecutive input images. We obtain two-layer networks that minimize this measure and show that some of them exhibit properties of complex cells but not clearly. We propose the sparseness of difference between responses to two consecutive inputs as an alternative measure of temporal coherence. We formulate an algorithm to maximize the sparseness of difference and show that complex cell properties emerge more clearly.

[1]  D. Burr,et al.  Functional implications of cross-orientation inhibition of cortical visual cells. I. Neurophysiological evidence , 1982, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  L. Maffei,et al.  I. Neurophysiological evidence , 1982 .

[3]  R. L. Valois,et al.  The orientation and direction selectivity of cells in macaque visual cortex , 1982, Vision Research.

[4]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[5]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[6]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[7]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[8]  D. Ruderman,et al.  INDEPENDENT COMPONENT ANALYSIS OF NATURAL IMAGE SEQUENCES YIELDS SPATIOTEMPORAL FILTERS SIMILAR TO SIMPLE CELLS IN PRIMARY VISUAL CORTEX , 1998 .

[9]  Aapo Hyvärinen,et al.  Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[10]  Konrad P. Körding,et al.  Extracting Slow Subspaces from Natural Videos Leads to Complex Cells , 2001, ICANN.

[11]  Aapo Hyvärinen,et al.  Complexity Pursuit: Separating Interesting Components from Time Series , 2001, Neural Computation.

[12]  Eero P. Simoncelli,et al.  Natural signal statistics and sensory gain control , 2001, Nature Neuroscience.

[13]  C. Zetzsche,et al.  Nonlinear and extra-classical receptive field properties and the statistics of natural scenes , 2001, Network.

[14]  Aapo Hyvärinen,et al.  Blind source separation by nonstationarity of variance: a cumulant-based approach , 2001, IEEE Trans. Neural Networks.

[15]  Christoph Kayser,et al.  Learning the invariance properties of complex cells from their responses to natural stimuli , 2002, The European journal of neuroscience.

[16]  Terrence J. Sejnowski,et al.  Slow Feature Analysis: Unsupervised Learning of Invariances , 2002, Neural Computation.

[17]  Aapo Hyvärinen,et al.  Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video , 2003, Neural Computation.

[18]  A. Hyvärinen,et al.  Temporal and spatiotemporal coherence in simple-cell responses: a generative model of natural image sequences , 2003, Network.

[19]  Laurenz Wiskott,et al.  Slow feature analysis yields a rich repertoire of complex cell properties. , 2005, Journal of vision.