Computational Model of the Cerebral Cortex That Performs Sparse Coding Using a Bayesian Network and Self-Organizing Maps

The authors have proposed a computational model of the cerebral cortex, called the BESOM model, that combines a Bayesian network and Self-Organizing Maps. In this paper, we add another model of the cerebral cortex, called sparse coding, into our model in a biologically plausible way. In the BESOM model, hyper-columns in the cerebral cortex are interpreted as random variables in a Bayesian network. We extend our model so that random variables can become "inactive." In addition, we apply bias at the time of recognition so that almost all of the random variables may become inactive. This mechanism realizes sparse coding without breaking the theoretical framework of the model based on the Bayesian networks.

[1]  K. Fukushima.  Neural network model for selective attention in visual pattern recognition and associative recall. , 1987, Applied optics.

[2]  Rajesh P. N. Rao,et al.  Bayesian inference and attentional modulation in the visual cortex , 2005, Neuroreport.

[3]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

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

[5]  H. Hosoya,et al.  Sparse codes of harmonic natural sounds and their modulatory interactions , 2009, Network.

[6]  Haruo Hosoya,et al.  A motor learning neural model based on Bayesian network and reinforcement learning , 2009, 2009 International Joint Conference on Neural Networks.

[7]  Julian Eggert,et al.  Bayesian Columnar Networks for Grounded Cognitive Systems , 2008 .

[8]  Yeuvo Jphonen,et al.  Self-Organizing Maps , 1995 .

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

[10]  Yuuji Ichisugi.  A Cerebral Cortex Model that Self-Organizes Conditional Probability Tables and Executes Belief Propagation , 2007, 2007 International Joint Conference on Neural Networks.

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

[12]  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.

[13]  Shimon Ullman,et al.  Cortical Circuitry Implementing Graphical Models , 2009, Neural Computation.

[14]  Tetsuo Furukawa,et al.  SOM of SOMs , 2009, Neural Networks.

[15]  D. George,et al.  A hierarchical Bayesian model of invariant pattern recognition in the visual cortex , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[16]  L. Andrew Coward.  The recommendation architecture: lessons from large-scale electronic systems applied to cognition , 2001, Cognitive Systems Research.

[17]  T. Poggio,et al.  What and where: A Bayesian inference theory of attention , 2010, Vision Research.

[18]  Koji Kurata,et al.  Separating visual information into position and direction by two inhibitory connected SOMs , 2004, Artificial Life and Robotics.

[19]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .