Stability in distribution of stochastic delay recurrent neural networks with Markovian switching. Issue 7 (October 2016)

• Record Type: Journal Article
• Authors: Zhu, Enwen; Yin, George; Yuan, Quan
• Is Part Of: Neural computing & applications. Volume 27:Issue 7(2016)
• Page Start: 2141
• Page End: 2151
• Publication Date: 2016-10
• Subjects: Stability in distribution -- Stochastic recurrent neural network -- Brownian motion -- Markov chain; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-2013-x
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract This paper investigates the stability in distribution of stochastic delay recurrent neural networks with Markovian switching. Using Lyapunov function and stochastic analysis techniques, sufficient conditions on the stability in distribution are given. For such recurrent neural networks, it reveals that the limit distribution of transition probability for segment process associated with solution process is indeed a unique ergodic invariant probability measure. Moreover, a numerical example is also provided to demonstrate the effectiveness and applicability of the theoretical results.