Please use this identifier to cite or link to this item: https://doi.org/10.1109/TNN.2004.824272
DC FieldValue
dc.titleMultistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions
dc.contributor.authorYi, Z.
dc.contributor.authorTan, K.K.
dc.date.accessioned2014-06-17T02:58:02Z
dc.date.available2014-06-17T02:58:02Z
dc.date.issued2004-03
dc.identifier.citationYi, 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
dc.identifier.issn10459227
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/56738
dc.description.abstractThis 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.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/TNN.2004.824272
dc.sourceScopus
dc.subjectComplete stability
dc.subjectDiscrete-time
dc.subjectGlobal attractivity
dc.subjectMultistability
dc.subjectNondivergence
dc.subjectRecurrent neural networks
dc.subjectUnsaturating piecewise linear activation functions
dc.typeArticle
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/TNN.2004.824272
dc.description.sourcetitleIEEE Transactions on Neural Networks
dc.description.volume15
dc.description.issue2
dc.description.page329-336
dc.description.codenITNNE
dc.identifier.isiut000220908300010
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

94
checked on Nov 9, 2019

WEB OF SCIENCETM
Citations

84
checked on Nov 1, 2019

Page view(s)

36
checked on Oct 28, 2019

Google ScholarTM

Check

Altmetric


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