Share Email Print
cover

Proceedings Paper

Optimum structure learning algorithms for competitive learning neural network
Author(s): Toshio Uchiyama; Mitsuhiro Sakai; Tomohide Saito; Taichi Nakamura
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A competitive learning neural network (CLNN) has a mechanism to discover statistically distinctive features included in input population. Competitive learning is different from a classification paradigm that needs a supervisor. Therefore, the unknown features are expected to be extracted from the visual image. However, CLNN has a problem of a serious decline of learning ability from the lack of competition. The reason for this is that the units of CLNN are not allocated to adapt to the distribution of input vectors in the feature space. We propose learning algorithms to optimize the positions of units and attain valid competition. These learning algorithms are based on structure learning according to two ideas. The first idea is that many units should be allocated according to concentrations of input vectors in the feature space. The second idea is that at least one unit should exist within an appropriate distance form every input vector. We apply the proposed algorithms to CLNN and experiment on the distinction of different binary 64 X 64 dot patterns. This patterns explores the validity of the two algorithms for CLNN.

Paper Details

Date Published: 1 April 1991
PDF: 12 pages
Proc. SPIE 1451, Nonlinear Image Processing II, (1 April 1991); doi: 10.1117/12.44325
Show Author Affiliations
Toshio Uchiyama, NTT Data Communications Systems Corp. (Japan)
Mitsuhiro Sakai, NTT Data Communications Systems Corp. (Japan)
Tomohide Saito, NTT Data Communications Systems Corp. (Japan)
Taichi Nakamura, NTT Data Communications Systems Corp. (Japan)


Published in SPIE Proceedings Vol. 1451:
Nonlinear Image Processing II
Edward R. Dougherty; Gonzalo R. Arce; Charles G. Boncelet, Editor(s)

© SPIE. Terms of Use
Back to Top