skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Pattern recognition using asymmetric attractor neural networks

Abstract

The asymmetric attractor neural networks designed by the Monte Carlo- (MC-) adaptation rule are shown to be promising candidates for pattern recognition. In such a neural network with relatively low symmetry, when the members of a set of template patterns are stored as fixed-point attractors, their attraction basins are shown to be isolated islands embedded in a ''chaotic sea.'' The sizes of these islands can be controlled by a single parameter. We show that these properties can be used for effective pattern recognition and rejection. In our method, the pattern to be identified is attracted to a template pattern or a chaotic attractor. If the difference between the pattern to be identified and the template pattern is smaller than a predescribed threshold, the pattern is attracted to the template pattern automatically and thus is identified as belonging to this template pattern. Otherwise, it wanders in a chaotic attractor for ever and thus is rejected as an unknown pattern. The maximum sizes of these islands allowed by this kind of neural networks are determined by a modified MC-adaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method formore » pattern recognition and rejection with an example of recognizing a set of Chinese characters.« less

Authors:
;  [1];  [2]
  1. Physics Department of Lanzhou University, Lanzhou 730000 (China)
  2. (China)
Publication Date:
OSTI Identifier:
20778464
Resource Type:
Journal Article
Resource Relation:
Journal Name: Physical Review. E, Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics; Journal Volume: 72; Journal Issue: 6; Other Information: DOI: 10.1103/PhysRevE.72.066111; (c) 2005 The American Physical Society; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; ASYMMETRY; ATTRACTORS; CHAOS THEORY; MONTE CARLO METHOD; NEURAL NETWORKS; PATTERN RECOGNITION; SYMMETRY

Citation Formats

Jin Tao, Zhao Hong, and Physics Department of Xiamen University, Xiamen 361005. Pattern recognition using asymmetric attractor neural networks. United States: N. p., 2005. Web. doi:10.1103/PHYSREVE.72.0.
Jin Tao, Zhao Hong, & Physics Department of Xiamen University, Xiamen 361005. Pattern recognition using asymmetric attractor neural networks. United States. doi:10.1103/PHYSREVE.72.0.
Jin Tao, Zhao Hong, and Physics Department of Xiamen University, Xiamen 361005. Thu . "Pattern recognition using asymmetric attractor neural networks". United States. doi:10.1103/PHYSREVE.72.0.
@article{osti_20778464,
title = {Pattern recognition using asymmetric attractor neural networks},
author = {Jin Tao and Zhao Hong and Physics Department of Xiamen University, Xiamen 361005},
abstractNote = {The asymmetric attractor neural networks designed by the Monte Carlo- (MC-) adaptation rule are shown to be promising candidates for pattern recognition. In such a neural network with relatively low symmetry, when the members of a set of template patterns are stored as fixed-point attractors, their attraction basins are shown to be isolated islands embedded in a ''chaotic sea.'' The sizes of these islands can be controlled by a single parameter. We show that these properties can be used for effective pattern recognition and rejection. In our method, the pattern to be identified is attracted to a template pattern or a chaotic attractor. If the difference between the pattern to be identified and the template pattern is smaller than a predescribed threshold, the pattern is attracted to the template pattern automatically and thus is identified as belonging to this template pattern. Otherwise, it wanders in a chaotic attractor for ever and thus is rejected as an unknown pattern. The maximum sizes of these islands allowed by this kind of neural networks are determined by a modified MC-adaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method for pattern recognition and rejection with an example of recognizing a set of Chinese characters.},
doi = {10.1103/PHYSREVE.72.0},
journal = {Physical Review. E, Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics},
number = 6,
volume = 72,
place = {United States},
year = {Thu Dec 15 00:00:00 EST 2005},
month = {Thu Dec 15 00:00:00 EST 2005}
}