Results 271 to 280 of about 56,788 (302)

Improved Stability Analysis for Delayed Neural Networks

IEEE Transactions on Neural Networks and Learning Systems, 2018
In this brief, by constructing an augmented Lyapunov-Krasovskii functional in a triple integral form, the stability analysis of delayed neural networks is investigated. In order to exploit more accurate bounds for the derivatives of triple integrals, new double integral inequalities are developed, which include some recently introduced estimation ...
Zhichen Li, Yan Bai, Congzhi Huang, Huaicheng Yan 0001, Shicai Mu   +4 more
openaire   +2 more sources

Global stability of neural networks with distributed delays

Physical Review E, 2003
In this paper, a model describing the dynamics of recurrent neural networks with distributed delays is considered. Some sufficient criteria are derived ensuring the global asymptotic stability of distributed-delay recurrent neural networks with more general signal propagation functions by introducing real parameters p>1, q(ij)>0, and r(jj)>0, i,j=1, em
openaire   +5 more sources

Delayed time series predictions with neural networks

Neurocomputing, 1998
Abstract Several recent studies have applied neural network models to the analysis and prediction of time series behaviour of solar activity. These studies have in general used overall measures of error magnitude to rate prediction accuracy. In this study, we concentrate on prediction of solar activity and demonstrate the tendency of neural networks ...
Andrew J. Conway, Keith P. Macpherson, John C. Brown   +2 more
openaire   +1 more source

Recurrent Neural Networks with Delays

1994
Recurrent neural networks (RNN) have been introduced for the modelization of non linear dynamic systems. In spite of their potential ability to implement systems of arbitrary complexity, they are often avoided because of large training times. For many problems, local recurrent networks or time delay feed forward architectures perform well enough.
J. Guignot, P. Gallinari
openaire   +1 more source

Stability for delayed reaction–diffusion neural networks

Physics Letters A, 2007
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Allegretto W., Papini D.
openaire   +6 more sources

Exponential Stability for Cellular Neural Networks with Delay

2006 13th IEEE International Conference on Electronics, Circuits and Systems, 2006
This paper investigates the exponential stability of a class of delayed cellular neural networks (DCNN's). By means of appropriately dividing the network state variables into several subgroups, the new sufficient exponential stability condition is derived by constructing Liapunov functional and using the method of the variation of constant.
Jinxiang Yang, Shouming Zhong, Xingwen Liu   +2 more
openaire   +1 more source

Exponential Convergence of Delayed Neural Networks

2005
Several new conditions for exponential convergence of DNN were proposed in this paper. These conditions guarantee the existence and uniqueness of equilibrium of DNN with certain different activation functions. To demonstrate the differences and features of the new criteria, some remarks are presented.
openaire   +1 more source

Delay-Dependent Stability Analysis for a Class of Delayed Neural Networks

2005
In this paper, we consider a class of time-delay artificial neural networks and obtain practical criteria to test asymptotic stability of the equilibrium of the time-delay artificial neural networks, with or without perturbations. These criteria require verification of the definiteness of a certain matrix, or verification of a certain inequality ...
Ru-Liang Wang, Yong-Qing Liu 0003
openaire   +1 more source

Synchronization of Coupled Connected Neural Networks With Delays

IEEE Transactions on Circuits and Systems I: Regular Papers, 2004
We investigate synchronization of an array of linearly coupled identical connected neural networks with delays; Variational method is used to investigate local synchronization. Global exponential stability is studied, too. We do not assume that the coupling matrix A is symmetric or irreducible.
Wenlian Lu, Tianping Chen
openaire   +1 more source

Synchronization of Delayed Fuzzy Cellular Neural Networks

2008 Fourth International Conference on Natural Computation, 2008
This paper studies synchronization of delayed fuzzy cellular neural networks. By the Lyapunov-Lasall principle of functional differential equations, some new stability criteria are obtained. The approaches developed here extend the ideas and techniques derived in recent literatures.
Wei Ding, Xiaoyi Fu
openaire   +1 more source