Please use this identifier to cite or link to this item: https://doi.org/10.1109/TCSI.2005.846664
DC FieldValue
dc.titleQualitative analysis for recurrent neural networks with linear threshold transfer functions
dc.contributor.authorTan, K.C.
dc.contributor.authorTang, H.
dc.contributor.authorZhang, W.
dc.date.accessioned2014-06-17T03:03:01Z
dc.date.available2014-06-17T03:03:01Z
dc.date.issued2005-05
dc.identifier.citationTan, K.C., Tang, H., Zhang, W. (2005-05). Qualitative analysis for recurrent neural networks with linear threshold transfer functions. IEEE Transactions on Circuits and Systems I: Regular Papers 52 (5) : 1003-1012. ScholarBank@NUS Repository. https://doi.org/10.1109/TCSI.2005.846664
dc.identifier.issn10577122
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/57165
dc.description.abstractMultistable networks have attracted much interest in recent years, since multistability is of primary importance for some applications of recurrent neural networks where monostability exhibits some restrictions. This paper focuses on the analysis of dynamical property for a class of additive recurrent neural networks with nonsaturating linear threshold transfer functions. A milder condition is derived to guarantee the boundedness and global attractivity of the networks as compared to that presented in [6]. Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically, and the relationships between the equilibria features and network parameters (synaptic weights and external inputs) are revealed. In addition, the sufficient and necessary conditions for coexistence of multiple equilibria are obtained, which confirmed the observations in [14] with a cortex-inspired silicon circuit. The results obtained in this paper are applicable to both symmetric and nonsymmetric networks. Simulation examples are used to illustrate the theory developed in this paper. © 2005 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/TCSI.2005.846664
dc.sourceScopus
dc.subjectEquilibria
dc.subjectGlobal attractivity
dc.subjectLinear threshod (LT) neural network
dc.subjectMultistability
dc.subjectNonsaturating
dc.typeArticle
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/TCSI.2005.846664
dc.description.sourcetitleIEEE Transactions on Circuits and Systems I: Regular Papers
dc.description.volume52
dc.description.issue5
dc.description.page1003-1012
dc.identifier.isiut000229054100018
Appears in Collections:Staff Publications

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

Google ScholarTM

Check

Altmetric


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