A hierarchical Bayesian model of invariant pattern recognition in the visual cortex

We describe a hierarchical model of invariant visual pattern recognition in the visual cortex. In this model, the knowledge of how patterns change when objects move is learned and encapsulated in terms of high probability sequences at each level of the hierarchy. Configuration of object parts is captured by the patterns of coincident high probability sequences. This knowledge is then encoded in a highly efficient Bayesian network structure. The learning algorithm uses a temporal stability criterion to discover object concepts and movement patterns. We show that the architecture and algorithms are biologically plausible. The large scale architecture of the system matches the large scale organization of the cortex and the micro-circuits derived from the local computations match the anatomical data on cortical circuits. The system exhibits invariance across a wide variety of transformations and is robust in the presence of noise. Moreover, the model also offers alternative explanations for various known cortical phenomena.

[1]  Edmund T. Rolls,et al.  Invariant Object Recognition in the Visual System with Novel Views of 3D Objects , 2002, Neural Computation.

[2]  T. Poggio,et al.  Predicting the visual world: silence is golden , 1999, Nature Neuroscience.

[3]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[4]  Suzanna Becker,et al.  Implicit Learning in 3D Object Recognition: The Importance of Temporal Context , 1999, Neural Computation.

[5]  David W. Arathorn,et al.  Map-Seeking Circuits in Visual Cognition: A Computational Mechanism for Biological and Machine Vision , 2002 .

[6]  Tai Sing Lee,et al.  Hierarchical Bayesian inference in the visual cortex. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[7]  A. Borst.  Seeing smells: imaging olfactory learning in bees , 1999, Nature Neuroscience.

[8]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

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

[10]  Karl Pfleger,et al.  On-Line Cumulative Learning of Hierarchical Sparse -grams , 2004 .

[11]  Paul Schrater,et al.  Shape perception reduces activity in human primary visual cortex , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[13]  Rajesh P. N. Rao,et al.  Development of localized oriented receptive fields by learning a translation-invariant code for natural images. , 1998, Network.

[14]  J. Hawkins,et al.  On Intelligence , 2004 .

[15]  P. Fldik,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Computation.

[16]  D C Van Essen,et al.  Information processing in the primate visual system: an integrated systems perspective. , 1992, Science.

[17]  Aapo Hyvärinen,et al.  Bubbles: a unifying framework for low-level statistical properties of natural image sequences. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  J. O'Regan,et al.  Some results on translation invariance in the human visual system. , 1990, Spatial vision.

[19]  A. Thomson,et al.  Interlaminar connections in the neocortex. , 2003, Cerebral cortex.

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

[21]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.