A Theory of Slow Feature Analysis for Transformation-Based Input Signals with an Application to Complex Cells

We develop a group-theoretical analysis of slow feature analysis for the case where the input data are generated by applying a set of continuous transformations to static templates. As an application of the theory, we analytically derive nonlinear visual receptive fields and show that their optimal stimuli, as well as the orientation and frequency tuning, are in good agreement with previous simulations of complex cells in primary visual cortex (Berkes and Wiskott, 2005). The theory suggests that side and end stopping can be interpreted as a weak breaking of translation invariance. Direction selectivity is also discussed.

[1]  Dawei W. Dong,et al.  Spatiotemporal Inseparability of Natural Images and Visual Sensitivities , 2001 .

[2]  D. N. Spinelli,et al.  Modification of the distribution of receptive field orientation in cats by selective visual exposure during development , 1971, Experimental Brain Research.

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

[4]  Laurenz Wiskott,et al.  Slowness and Sparseness Lead to Place, Head-Direction, and Spatial-View Cells , 2007, PLoS Comput. Biol..

[5]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[6]  Y. Miyashita.  Neuronal correlate of visual associative long-term memory in the primate temporal cortex , 1988, Nature.

[7]  E. M. Lifshitz,et al.  Quantum mechanics: Non-relativistic theory, , 1959 .

[8]  D. O'Leary,et al.  Molecular gradients and development of retinotopic maps. , 2005, Annual review of neuroscience.

[9]  S. Gerber,et al.  Unsupervised Natural Experience Rapidly Alters Invariant Object Representation in Visual Cortex , 2008 .

[10]  Konrad Paul Kording,et al.  How are complex cell properties adapted to the statistics of natural stimuli? , 2004, Journal of neurophysiology.

[11]  William Bialek,et al.  Statistics of Natural Images: Scaling in the Woods , 1993, NIPS.

[12]  David J. Field,et al.  Innate Visual Learning through Spontaneous Activity Patterns , 2008, PLoS Comput. Biol..

[13]  D. Ringach.  On the Origin of the Functional Architecture of the Cortex , 2007, PloS one.

[14]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[15]  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.

[16]  Niko Wilbert,et al.  Learning complex cell units from simulated prenatal retinal waves with slow feature analysis , 2009, BMC Neuroscience.

[17]  Laurenz Wiskott,et al.  Slow Feature Analysis: A Theoretical Analysis of Optimal Free Responses , 2003, Neural Computation.

[18]  Y. Dan,et al.  Stimulus Timing-Dependent Plasticity in Cortical Processing of Orientation , 2001, Neuron.

[19]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[20]  Rajesh P. N. Rao,et al.  Learning the Lie Groups of Visual Invariance , 2007, Neural Computation.

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

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

[23]  D. Hubel,et al.  RECEPTIVE FIELDS OF CELLS IN STRIATE CORTEX OF VERY YOUNG, VISUALLY INEXPERIENCED KITTENS. , 1963, Journal of neurophysiology.

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

[25]  Rajesh P. N. Rao,et al.  Learning Lie Groups for Invariant Visual Perception , 1998, NIPS.

[26]  J. Atick,et al.  STATISTICS OF NATURAL TIME-VARYING IMAGES , 1995 .

[27]  Laurenz Wiskott,et al.  Slow Feature Analysis: Perspectives for Technical Applications of a Versatile Learning Algorithm , 2012, KI - Künstliche Intelligenz.