Suitability of V1 Energy Models for Object Classification

Simulations of cortical computation have often focused on networks built from simplified neuron models similar to rate models hypothesized for V1 simple cells. However, physiological research has revealed that even V1 simple cells have surprising complexity. Our computational simulations explore the effect of this complexity on the visual system's ability to solve simple tasks, such as the categorization of shapes and digits, after learning from a limited number of examples. We use recently proposed high-throughput methodology to explore what axes of modeling complexity are useful in these categorization tasks. We find that complex cell rate models learn to categorize objects better than simple cell models, and without incurring extra computational expense. We find that the squaring of linear filter responses leads to better performance. We find that several other components of physiologically derived models do not yield better performance.

[1]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[2]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[3]  John R. Anderson,et al.  The Adaptive Character of Thought , 1990 .

[4]  Nathan Intrator,et al.  Complex cells and Object Recognition , 1997 .

[5]  D. Ferster,et al.  Computational Diversity in Complex Cells of Cat Primary Visual Cortex , 2007, The Journal of Neuroscience.

[6]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[7]  David D. Cox,et al.  A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation , 2009, PLoS Comput. Biol..

[8]  Duane Q Nykamp,et al.  Full identification of a linear-nonlinear system via cross-correlation analysis. , 2002, Journal of vision.

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[10]  Thomas Serre,et al.  A quantitative theory of immediate visual recognition. , 2007, Progress in brain research.

[11]  K. Naka,et al.  S‐potentials from luminosity units in the retina of fish (Cyprinidae) , 1966, The Journal of physiology.

[12]  Bartlett W. Mel,et al.  Dendrites: bug or feature? , 2003, Current Opinion in Neurobiology.

[13]  Paul A. Rhodes Recoding Patterns of Sensory Input: Higher-Order Features and the Function of Nonlinear Dendritic Trees , 2008, Neural Computation.

[14]  Eero P. Simoncelli,et al.  Spatiotemporal Elements of Macaque V1 Receptive Fields , 2005, Neuron.

[15]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[16]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[17]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[18]  Michael S. Lewicki,et al.  A Theory of Retinal Population Coding , 2006, NIPS.

[19]  C. Malsburg,et al.  The role of complex cells in object recognition , 2002, Vision Research.

[20]  D. Ringach,et al.  Dynamics of Spatial Frequency Tuning in Macaque V1 , 2002, The Journal of Neuroscience.

[21]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[22]  D. Heeger Normalization of cell responses in cat striate cortex , 1992, Visual Neuroscience.

[23]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[24]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[25]  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.

[26]  David J. Field,et al.  How Close Are We to Understanding V1? , 2005, Neural Computation.

[27]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[28]  Tomaso A. Poggio,et al.  A Canonical Neural Circuit for Cortical Nonlinear Operations , 2008, Neural Computation.

[29]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[30]  R. Fergus,et al.  Learning invariant features through topographic filter maps , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.