Local and Global Stability Analysis of an Unsupervised Competitive Neural Network

Unsupervised competitive neural networks (UCNN) are an established technique in pattern recognition for feature extraction and cluster analysis. A novel model of an unsupervised competitive neural network implementing a multitime scale dynamics is proposed in this letter. The local and global asympt...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2008-02, Vol.19 (2), p.346-351
Main Authors: Meyer-Base, A., Thummler, V.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Competition
Computer science
control theory
systems
Computer Simulation
Equations
Exact sciences and technology
Hardware
Humans
Information Storage and Retrieval
lateral inhibition
Learning systems
multitime scale system
Neural networks
Neural Networks (Computer)
Neurofeedback
Neurons
Nonlinear dynamical systems
nonlinear dynamics
Pattern recognition
Pattern Recognition, Automated
Stability analysis
Very large scale integration
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Unsupervised competitive neural networks (UCNN) are an established technique in pattern recognition for feature extraction and cluster analysis. A novel model of an unsupervised competitive neural network implementing a multitime scale dynamics is proposed in this letter. The local and global asymptotic stability of the equilibrium points of this continuous-time recurrent system whose weights are adapted based on a competitive learning law is mathematically analyzed. The proposed neural network and the derived results are compared with those obtained from other multitime scale architectures.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/TNN.2007.908626