Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition

Abstract

An application of laterally interconnected self-organizing maps (LISSOM) to handwritten digit recognition is presented. The lat(cid:173) eral 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 redun(cid:173) dant activity on the map. The map thus forms internal representa(cid:173) tions 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.

Cite

Text

Choe et al. "Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition." Neural Information Processing Systems, 1995.

Markdown

[Choe et al. "Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/choe1995neurips-laterally/)

BibTeX

@inproceedings{choe1995neurips-laterally,
  title     = {{Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition}},
  author    = {Choe, Yoonsuck and Sirosh, Joseph and Miikkulainen, Risto},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {736-742},
  url       = {https://mlanthology.org/neurips/1995/choe1995neurips-laterally/}
}