Please use this identifier to cite or link to this item: https://doi.org/10.1109/TNN.2004.824272
Title: Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions
Authors: Yi, Z.
Tan, K.K. 
Keywords: Complete stability
Discrete-time
Global attractivity
Multistability
Nondivergence
Recurrent neural networks
Unsaturating piecewise linear activation functions
Issue Date: Mar-2004
Source: Yi, Z.,Tan, K.K. (2004-03). Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. IEEE Transactions on Neural Networks 15 (2) : 329-336. ScholarBank@NUS Repository. https://doi.org/10.1109/TNN.2004.824272
Abstract: This paper studies the multistability of a class of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. It addresses the nondivergence, global attractivity, and complete stability of the networks. Using the local inhibition, conditions for nondivergence are derived, which not only guarantee nondivergence, but also allow for the existence of multiequilibrium points. Under these nondivergence conditions, global attractive compact sets are obtained. Complete stability is studied via constructing novel energy functions and using the well-known Cauchy Convergence Principle. Examples and simulation results are used to illustrate the theory.
Source Title: IEEE Transactions on Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/56738
ISSN: 10459227
DOI: 10.1109/TNN.2004.824272
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

105
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.