Laterally Interconnected Self-Organizing Maps In Hand-Written Digit Recognition (1996)
An application of laterally interconnected self-organizing maps (LISSOM) to handwritten digit recognition is presented. The lateral connections learn the correlations of activity between units on the map. The resulting excitatory connections focus the activity into local patches and the inhibitory connections decorrelate redundant activity on the map. The map thus forms internal representations that are easy to recognize with e.g. a perceptron network. The recognition rate on a subset of NIST database 3 is 4.0% higher with LISSOM than with a regular Self-Organizing Map (SOM) as the front end, and 15.8% higher than recognition of raw input bitmaps directly. These results form a promising starting point for building pattern recognition systems with a LISSOM map as a front end.
In David S. Touretzky and Michael C. Mozer and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, 736-742, 1996. Cambridge, MA: MIT Press.

Yoonsuck Choe Ph.D. Alumni choe [at] tamu edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Joseph Sirosh Ph.D. Alumni joseph sirosh [at] gmail com

The LISSOM package contains the C++, Python, and Scheme source code and examples for training and testing firing-rate...