An application of biologically motivated laterally interconnected synergetically self-organizing maps (LISSOM) to off-line recognition of handwritten digit is presented. The lateral connections of the LISSOM map learns the correlation between units through Hebbian learning. As a result, the excitatory connections focus the activity in local patches and lateral connections decorrelate redundant activity on the map. This process forms internal representations for the input that are easier to recognize than the input bitmaps themselves or the activation patterns on a standard Self-Organizing Map (SOM). The recognition rate on a publically available subset of NIST special database 3 with LISSOM is 4.0% higher than that based on SOM, and 15.8% higher than that based on raw input bitmaps. These results form a promising starting point for building pattern recognition systems with a LISSOM map as a front end.

PS

Masters Thesis, Department of Computer Sciences, The University of Texas at Austin, Austin, TX, 1995. 65. Technical Report AI95-236.

@MastersThesis{choe:ms, title={Laterally Interconnected Self-Organizing Feature Map In Handwritten Digit Recognition}, author={Yoonsuck Choe}, school={Department of Computer Sciences, The University of Texas at Austin}, address={Austin, TX}, pages={65}, note={Technical Report AI95-236}, url="http://nn.cs.utexas.edu/?choe:ms95", year={1995} }