Results 251 to 260 of about 56,788 (302)

Stability of stochastic delay neural networks

Journal of the Franklin Institute, 2001
The stochastically perturbed network with delays \[ dx(t)= \bigl[ -Bx(t)+ Ag\bigl(x_\tau (t)\bigr) \biggr]dt +\sigma\bigl( x(t),x_\tau (t), t\bigr)dw(t), t\geq 0;\;x(s)=\xi(s),\;-\tau\leq s\leq 0;\tag{1} \] is considered. Here \(w(t)\) is an \(m\)-dimensional Brownian motion, \(\sigma(x,y,t)\) is locally Lipschitz continuous and satisfies the linear ...
Blythe, Steve, Mao, Xuerong, Liao, Xiaoxin   +2 more
openaire   +3 more sources

On delayed impulsive Hopfield neural networks

Neural Networks, 1999
Many evolutionary processes, particularly some biological systems, exhibit impulsive dynamical behaviors, which can be well described by impulsive Hopfield neural networks. This paper formulates and studies a model of delayed impulsive Hopfield neural networks. Several fundamental issues such as global exponential stability, existence and uniqueness of
Zhi-Hong Guan, Guanrong Chen
openaire   +1 more source

An analysis of exponential stability of delayed neural networks with time varying delays

Neural Networks, 2004
This paper derives a new sufficient condition for the exponential stability of the equilibrium point for delayed neural networks with time varying delays by employing a Lyapunov-Krasovskii functional and using Linear Matrix Inequality (LMI) approach ...
Sabri Arik
exaly   +2 more sources

FAST TIME DELAY NEURAL NETWORKS

International Journal of Neural Systems, 2005
This paper presents a new approach to speed up the operation of time delay neural networks. The entire data are collected together in a long vector and then tested as a one input pattern. The proposed fast time delay neural networks (FTDNNs) use cross correlation in the frequency domain between the tested data and the input weights of neural networks.
Hazem M. El-Bakry, Qiangfu Zhao
openaire   +2 more sources

Exponential periodicity of neural networks with delays

Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03., 2003
In this paper, exponential periodicity of neural networks with delays is proposed. Without assuming the boundedness, monotonicity and differentiability of the activation functions, some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural networks with delays are obtained.
Changyin Sun 0001, Changgui Sun, Chun-Bo Feng   +2 more
openaire   +1 more source

Pinning synchronization of delayed neural networks

Chaos: An Interdisciplinary Journal of Nonlinear Science, 2008
This paper investigates adaptive pinning synchronization of a general weighted neural network with coupling delay. Unlike recent works on pinning synchronization which proposed the possibility that synchronization can be reached by controlling only a small fraction of neurons, this paper aims to answer the following question: Which neurons should be ...
Zhou, J, Wu, X, Yu, W, Small, M, Lu, JA
openaire   +3 more sources

Multistability and bifurcation in a delayed neural network

Neurocomputing, 2016
In this paper, the dynamical behaviors including multistability and bifurcation of a delayed neural network system are investigated. It is shown that the system coexists sixteen stable states with their own domains of attraction. All stable states are determined by using a Lyapunov function.
Qiang Lai, Bin Hu 0008, Zhi-Hong Guan, Tao Li 0017, Ding-Fu Zheng, Yonghong Wu   +5 more
openaire   +1 more source

Dynamics in a delayed-neural network☆

Chaos, Solitons & Fractals, 2007
The following delay-differential system is considered \[ \dot x_j(t)=-x_j(t) +\alpha f(x_j(t-\tau_s)) + \beta\left[ g(x_{j-1}(t-\tau_1))+g(x_{j+1}(t-\tau_1)) \right] + \gamma h(x_{j+2}(t-\tau_2)), \] where the index \(j\) is considered modulo 4 and the functions \(f,g,h\) vanish at zero.
openaire   +1 more source

System Identification with Delayed Neural Network

2008 Fourth International Conference on Natural Computation, 2008
In this brief, the identification problem for time-varying delay nonlinear system is discussed. We use a delayed dynamic neural network to do on-line identification. This neural network has dynamic series-parallel structure. The stability conditions of on-line identification are derived by Lyapunov-Krasovskii approach. The weights of the delayed neural
Pu Wang, Xueli Wu, Bin Wang, Jianhua Zhang 0010   +3 more
openaire   +1 more source

Delay-Dependent State Estimation for Delayed Neural Networks

IEEE Transactions on Neural Networks, 2006
In this letter, the delay-dependent state estimation problem for neural networks with time-varying delay is investigated. A delay-dependent criterion is established to estimate the neuron states through available output measurements such that the dynamics of the estimation error is globally exponentially stable. The proposed method is based on the free-
Yong He 0003, Qing-Guo Wang, Min Wu 0002, Chong Lin   +3 more
openaire   +2 more sources