On global asymptotic stability of fully connected recurrent neural networks

Conditions for global asymptotic stability (GAS) of a nonlinear relaxation process realized by a recurrent neural network (RNN) are provided. Existence, convergence, and robustness of such a process are analyzed. This is undertaken based upon the contraction mapping theorem (CMT) and the correspondi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mandic, D.P., Chambers, J.A., Bozic, M.M.
Format: Conference Proceeding
Language:English
Subjects:
Asymptotic stability
Constraint optimization
Convergence
Dynamic programming
Linear systems
Neural networks
Neurons
Nonlinear equations
Recurrent neural networks
Robustness
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Conditions for global asymptotic stability (GAS) of a nonlinear relaxation process realized by a recurrent neural network (RNN) are provided. Existence, convergence, and robustness of such a process are analyzed. This is undertaken based upon the contraction mapping theorem (CMT) and the corresponding fixed point iteration (FPI). Upper bounds for such a process are shown to be the conditions of convergence for a commonly analyzed RNN with a linear state dependence.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2000.860132