lim-discretetimestochastic-2020.pdf (446.86 kB)
Discrete-time stochastic quaternion-valued neural networks with time delays: an asymptotic stability analysis
journal contribution
posted on 2020-06-01, 00:00 authored by R Sriraman, G Rajchakit, Chee Peng LimChee Peng Lim, P Chanthorn, R SamiduraiStochastic disturbances often cause undesirable characteristics in real-world system modeling. As a result, investigations on stochastic disturbances in neural network (NN) modeling are important. In this study, stochastic disturbances are considered for the formulation of a new class of NN models; i.e., the discrete-time stochastic quaternion-valued neural networks (DSQVNNs). In addition, the mean-square asymptotic stability issue in DSQVNNs is studied. Firstly, we decompose the original DSQVNN model into four real-valued models using the real-imaginary separation method, in order to avoid difficulties caused by non-commutative quaternion multiplication. Secondly, some new sufficient conditions for the mean-square asymptotic stability criterion with respect to the considered DSQVNN model are obtained via the linear matrix inequality (LMI) approach, based on the Lyapunov functional and stochastic analysis. Finally, examples are presented to ascertain the usefulness of the obtained theoretical results.
History
Journal
SymmetryVolume
12Issue
6Article number
936Pagination
1 - 26Publisher
MDPI AGLocation
Basel, SwitzerlandPublisher DOI
Link to full text
eISSN
2073-8994Language
engPublication classification
C1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
stochastic disturbancesquaternion-valued neural networksreal-imaginary separation methodLyapunov fractionallinear matrix inequalityScience & TechnologyMultidisciplinary SciencesScience & Technology - Other TopicsGLOBAL EXPONENTIAL STABILITYTO-STATE STABILITYPASSIVITY ANALYSISASSOCIATIVE MEMORYLEAKAGE DELAYDISSIPATIVITY
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC