UTCS Artificial Intelligence
LISSOM: Laterally Interconnected Self-Organizing Maps
Active from 1987 - 1997
LISSOM is a biologically more realistic implementation of the SOM idea, where the weight change neighborhood is determined through competition and collaboration mediated by lateral connections (instead of a global supervisor), and weights are changed based on Hebbian learning and renormalization (instead of Euclidean distance). LISSOM was developed as a first step towards modeling biological maps (see the visual cortex page), but it also has useful properties in its own right. It is capable of self-organization roughly similar to the SOM model, but because the lateral connections decorrelate the activation patterns on the map, they form a better internal representation for visual patterns such as those in handwritten digit recognition.
joseph sirosh [at] gmail com
choe [at] tamu edu
risto [at] cs utexas edu
Tilt Aftereffects in a Self-Organizing Model of the Primary Visual Cortex
James A. Bednar, Masters Thesis, Department of Computer Sciences, The University of Texas at Austin. Technical Report AI97-259.
Unsupervised Learning, Clustering, and Self-Organization
Austin Arboretum Foliage Corpus
Photographs for use with color modeling work taken by Judah De Paula at the Austin Arboretum. Images contain mostly leav...
Flowers Color Image Corpus
Photographs for use with color modeling work taken by Judah De Paula at the Austin Arboretum. Images contain mostly clos...