Optimum structure learning algorithms for competitive learning neural network

Toshio Uchiyama; Mitsuhiro Sakai; Tomohide Saito; Taichi Nakamura

doi:10.1117/12.44325

1 April 1991 Optimum structure learning algorithms for competitive learning neural network

Toshio Uchiyama, Mitsuhiro Sakai, Tomohide Saito, Taichi Nakamura

Proceedings Volume 1451, Nonlinear Image Processing II; (1991) https://doi.org/10.1117/12.44325
Event: Electronic Imaging '91, 1991, San Jose, CA, United States

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.

Citation Download Citation

Toshio Uchiyama, Mitsuhiro Sakai, Tomohide Saito, and Taichi Nakamura "Optimum structure learning algorithms for competitive learning neural network", Proc. SPIE 1451, Nonlinear Image Processing II, (1 April 1991); https://doi.org/10.1117/12.44325

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available