Results 261 to 270 of about 56,788 (302)

Complete Stability in Multistable Delayed Neural Networks

Neural Computation, 2009
We investigate the complete stability for multistable delayed neural networks. A new formulation modified from the previous studies on multistable networks is developed to derive componentwise dynamical property. An iteration argument is then constructed to conclude that every solution of the network converges to a single equilibrium as time tends to ...
Chang-Yuan Cheng, Chih-Wen Shih
openaire   +2 more sources

Training Delays in Spiking Neural Networks

2019
Spiking Neural Networks (SNNs) are a promising computational paradigm, both to understand biological information processing and for low-power, embedded chips. Although SNNs are known to encode information in the precise timing of spikes, conventional artificial learning algorithms do not take this into account directly.
Laura State, Pau Vilimelis Aceituno
openaire   +2 more sources

Global Convergence of Delayed Neural Network Systems

International Journal of Neural Systems, 2003
In this paper, without assuming the boundedness, strict monotonicity and differentiability of the activation functions, we utilize a new Lyapunov function to analyze the global convergence of a class of neural networks models with time delays. A new sufficient condition guaranteeing the existence, uniqueness and global exponential stability of the ...
Wenlian Lu, Libin Rong, Tianping Chen
openaire   +2 more sources

Stochastic Stabilization of Delayed Neural Networks

2007
By introducing appropriate stochastic factors into the neural networks, there were results showing that the neural networks can be stabilized. In this paper, stochastic stabilization of delayed neural networks is studied. First, a new type Razumikhin-type theorem about stochastic functional differential equations is proposed and the rigid proof is ...
Wudai Liao, Jinghuan Chen, Yulin Xu, Xiaoxin Liao   +3 more
openaire   +1 more source

SYNCHRONIZATION AND DESYNCHRONIZATION IN A DELAYED DISCRETE NEURAL NETWORK

International Journal of Bifurcation and Chaos, 2007
In this paper, we consider a delayed discrete neural network of two identical neurons with excitory interactions. After investigating the stability of the given system, we establish a new scheme, and use the scheme to analyze the possible bifurcations occurring in the model.
Mingshu Peng, Yuan Yuan 0008
openaire   +1 more source

A neural network delay compensator for networked control systems

2008 IEEE International Conference on Emerging Technologies and Factory Automation, 2008
This paper presents a neural network implementation of the delay compensator to reduce the variable sampling to actuation delay effects in networked control systems. The compensator action is based on the knowledge of the sampling to actuation delay affecting the system and the control signal.
Ana Antunes, Fernando Morgado Dias, Alexandre Manuel Mota   +2 more
openaire   +1 more source

Synchronization of chaotic neural networks with delay in irregular networks

Applied Mathematics and Computation, 2008
This paper studies the synchronization in cellular neural networks (CNNs). For the individual oscillator, the following differential delay system is taken \[ \dot x(t)=0.001x(t)-3.8(| x_\tau +1 |-|x_\tau-1|)+ 2.85\left(\left| x_\tau+\frac{4}{3}\right| - \left| x_\tau-\frac{4}{3}\right| \right), \] where \(x_\tau=x(t-\tau)\).
Cornelio Posadas-Castillo, César Cruz-Hernández, Rosa Martha López-Gutiérrez   +2 more
openaire   +2 more sources

Chaotic Synchronization of Delayed Neural Networks

2005
In this paper, synchronization issue of a coupled time-delayed neural system with chaos is investigated. A sufficient condition for determining the exponential synchronization between the drive and response systems is derived via Lyapunov-Krasovskii stability theorem.
Fenghua Tu, Xiaofeng Liao 0001, Chuandong Li 0001   +2 more
openaire   +1 more source

DELAY-DEPENDENT AND DELAY-INDEPENDENT STABILITY CRITERIA FOR CELLULAR NEURAL NETWORKS WITH DELAYS

International Journal of Bifurcation and Chaos, 2006
The stability issues of the equilibrium points of the cellular neural networks (CNN) with single and multiple delays are further investigated. Several novel delay-dependent and delay-independent asymptotical/exponential stability criteria are established by employing parameterized first-order model transformation, Lyapunov–Krasovskii stability theorem
Chuandong Li 0001, Xiaofeng Liao 0001, Kwok-Wo Wong   +2 more
openaire   +1 more source

Stability criteria for delayed neural networks

Physical Review E, 2001
In this paper, delay-independent global asymptotic and exponential stability for a class of delayed neural networks (DNN's) is investigated, and some criteria are established to ensure stability of DNN's by applying the Lyapunov direct method. These criteria are expressed by imposing constraints on weight matrices of the networks, and they are easy to ...
openaire   +2 more sources