Stability and Synchronization Control of Stochastic Neural by Wuneng Zhou, Jun Yang, Liuwei Zhou, Dongbing Tong

By Wuneng Zhou, Jun Yang, Liuwei Zhou, Dongbing Tong

This booklet experiences at the most recent findings within the learn of Stochastic Neural Networks (SNN). The booklet collects the radical version of the disturbance pushed by way of Levy technique, the examine approach to M-matrix, and the adaptive regulate approach to the SNN within the context of balance and synchronization keep watch over. The ebook may be of curiosity to school researchers, graduate scholars up to the mark technology and engineering and neural networks who desire to study the center ideas, equipment, algorithms and functions of SNN.

Show description

Read Online or Download Stability and Synchronization Control of Stochastic Neural Networks PDF

Similar networks books

Computer Networks (4th Edition) - Problem Solutions

Whole strategies for laptop Networks (4th version) by means of Andrew Tanenbaum.

Advances in Neural Networks - ISNN 2010: 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part I

This e-book and its sister quantity gather refereed papers awarded on the seventh Inter- tional Symposium on Neural Networks (ISNN 2010), held in Shanghai, China, June 6-9, 2010. construction at the good fortune of the former six successive ISNN symposiums, ISNN has develop into a well-established sequence of well known and fine quality meetings on neural computation and its purposes.

Sensor Networks and Configuration: Fundamentals, Standards, Platforms, and Applications

Advances in networking impact many forms of tracking and keep an eye on structures within the so much dramatic manner. Sensor community and configuration falls below the class of recent networking structures. instant Sensor community (WSN) has emerged and caters to the necessity for real-world purposes. technique and layout of WSN represents a wide learn subject with purposes in lots of sectors resembling undefined, domestic, computing, agriculture, surroundings, etc, in accordance with the adoption of primary rules and the state of the art know-how.

Extra resources for Stability and Synchronization Control of Stochastic Neural Networks

Example text

7) achieve synchronization. Next, we denote ei (t) = xi (t) −r (t), which indicates the error signal. 6), the error signal system can be easily obtained as follows: ⎡ t dei (t) = ⎣−Cei (t) + Ag(ei (t)) + Bg(ei (t − τ )) + W ⎤ g(ei (s))ds ⎦ dt t−τ N + ci N G i j Γ e j (t)d Wi1 (t) + di j=1 G i j Γτ e j (t − τ )d Wi2 (t) + Ui dt, i = 1, 2, . . 11) where g(ei (t)) = f (ei (t) + r (t)) − f (r (t)) and g(ei (t − τ )) = f (ei (t − τ ) + r (t − τ )) − f (r (t − τ )). 12) where M = diag{β1 , β2 , β3 , .

Appl. 38(1), 121– 130 (2011) 4. R. Belohlavek, Fuzzy logical bidirectional associative memory. Inf. Sci. 128(1), 91–103 (2000) 5. J. Cao, P. Li, W. Wang, Global synchronization in arrays of delayed neural networks with constant and delayed coupling. Phys. Lett. A 353(4), 318–325 (2006) 6. J. Cao, X. Li, Stability in delayed Cohen-Grossberg neural networks: LMI optimization approach. Phys. D 212(1), 54–65 (2005) 7. J. Cao, Z. Wang, Y. Sun, Synchronization in an array of linearly stochastically coupled networks with time-delays.

5) j=1 where xi (t) = [xi1 (t), xi2 (t), . . , xin (t)]T ∈ Rn (i = 1, 2, . . , N ) is the state vector associated with the ith DNNs; f (xi (t)) = [ f 1 (xi1 (t)), f 2 (xi2 (t)), . . , f n (xin (t))]T ∈ Rn is the activation functions of the neurons with f (0) = 0; C = diag{c1 , c2 , . . , cn } > 0 is a diagonal matrix that shows the rate of the ith unit resetting its potential to the resting state in isolation when disconnected from the external inputs and the network; A = (ai j )n×n and B = (bi j )n×n stand for, respectively, the connection weight matrix and the discretely delayed connection weight matrix; Wi = [Wi1 , Wi2 ]T are two-dimensional Brownian motions; Γ ∈ Rn×n and Γτ ∈ Rn×n denotes the internal coupling of the network at time t and t − τ , where τ > 0 is the time-delay; ci and di indicate the intensity of the noise; Ui is the input of the controller; G = (G i j ) N ×N describes the topological structure and the coupling strength of the networks, and it meet the following conditions [27]: N G ii = − Gi j .

Download PDF sample

Rated 4.73 of 5 – based on 42 votes