Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

August 15, 1997, Vol. 9, No. 6, Pages 1321-1344
(doi: 10.1162/neco.1997.9.6.1321)
© 1997 Massachusetts Institute of Technology
Self-Organized Formation of Various Invariant-Feature Filters in the Adaptive-Subspace SOM
Article PDF (405.05 KB)
Abstract

The adaptive-subspace self-organizing map (ASSOM) is a modular neural network architecture, the modules of which learn to identify input patterns subject to some simple transformations. The learning process is unsupervised, competitive, and related to that of the traditional SOM (self-organizing map). Each neural module becomes adaptively specific to some restricted class of transformations, and modules close to each other in the network become tuned to similar features in an orderly fashion. If different transformations exist in the input signals, different subsets of ASSOM units become tuned to these transformation classes.