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 fixedpoint 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 MCadaptation rule which are shown to be able to dramatically enlarge the sizes of the islands. We illustrate the use of our method formore »
 Authors:
 Physics Department of Lanzhou University, Lanzhou 730000 (China)
 (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 fixedpoint 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 MCadaptation 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}
}

A methodology for evaluation of transient stability of medium size interconnected longitudinal power systems has been developed using a hybrid neural network/pattern recognition approach. Assessment of transient stability is done using fast pattern recognition algorithm at each load level, accurately predicted by a neural network on a halfhourly basis. As opposed to conventional approaches, this hybrid strategy can make fast decisions with less computations.

Spatial asymmetric retrieval states in binary attractor neural network
In this paper we show that during the retrieval process in a binary Hebb attractor neural network, spatial localized states can be observed when the connectivity of the network is distancedependent and there is an asymmetry between the retrieval and the learning states. 
Pattern recognition using neural networks. Technical report, August 1, 1994September 11, 1994
I am pleased to submit the following technical report to Oak Ridge National Laboratories as an accomplishment of the 6 (six) week appointment in the U.S. Nuclear Regulatory Commission`s Historically Black College and Universities Faculty Research Participation Program, Summer 1994 (August  September 11, 1994). In this project, an approach for pattern recognition using neural networks is proposed. Particularly, a Boltzmann machine, a Hopfield neural net model, is used in pattern recognition with desirable learning ability. The Boltzmann machine features stochastic learning, which acts as the connection dynamics for determining the weights on the connections between the neuronlike cells (processingmore » 
Reconstruction of the El Nino attractor with neural networks
Based on a combined data set of sea surface temperature, zonal surface wind stress and upper ocean heat content the dynamics of the El Nino phenomenon is investigated. In a reduced phase space spanned by the first four EOFs two different stochastic models are estimated from the data. A nonlinear model represented by a simulated neural network is compared with a linear model obtained with the principal oscillation pattern (POP) analysis. While the linear model is limited to damped oscillations onto a fix point attractor, the nonlinear model recovers a limit cycle attractor. This indicates that the real system ismore » 
Periodic solution and chaotic strange attractor for shunting inhibitory cellular neural networks with impulses
By using the continuation theorem of coincidence degree theory and constructing suitable Lyapunov functions, we study the existence, uniqueness, and global exponential stability of periodic solution for shunting inhibitory cellular neural networks with impulses, dx{sub ij}/dt=a{sub ij}x{sub ij}{sigma}{sub C{sub K}{sub 1}}{sub (setmembershipsign)=N{sub r}{sub (i,j)}C{sub ij}{sup kl}f{sub ij}[x{sub kl}(t)]x{sub ij}+L{sub ij}(t), t>0,t{ne}t{sub k}; {delta}x{sub ij}(t{sub k})=x{sub ij}(t{sub k}{sup +})x{sub ij}(t{sub k}{sup })=I{sub k}[x{sub ij}(t{sub k})], k=1,2,... . Furthermore, the numerical simulation shows that our system can occur in many forms of complexities, including periodic oscillation and chaotic strange attractor. To the best of our knowledge, these results have been obtained formore »