9 May 2006 Dynamical aspects of multi-time scale unsupervised neural networks
Author Affiliations +
Proceedings Volume 6229, Intelligent Computing: Theory and Applications IV; 62290V (2006); doi: 10.1117/12.668681
Event: Defense and Security Symposium, 2006, Orlando (Kissimmee), Florida, United States
Abstract
Multi-time scale unsupervised neural networks (MTSUNN) represent an established technique in pattern recognition for feature extraction and cluster analysis. From the nonlinear systems analysis perspective, they implement a very complex coupled multi-mode dynamics. This paper gives a comprehensive overview of several neural architectures of a combined activity and weights dynamics. The global asymptotic and exponential stability of the equilibrium points of these continuous-time recurrent systems whose weights are adapted based on unsupervised learning laws are mathematically analyzed. The derived architectures can lead to hybrid implementations in VLSI techniques.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Anke Meyer-Bäse, Shantanu Joshi, Helge Ritter, "Dynamical aspects of multi-time scale unsupervised neural networks", Proc. SPIE 6229, Intelligent Computing: Theory and Applications IV, 62290V (9 May 2006); doi: 10.1117/12.668681; https://doi.org/10.1117/12.668681
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Neural networks

Neurons

Scanning tunneling microscopy

Differential equations

Systems modeling

Machine learning

Very large scale integration

Back to Top