Multi-user detection using time-varying scaling-parameter transiently chaotic neural networks

1999 ◽  
Vol 35 (12) ◽  
pp. 987 ◽  
Author(s):  
W. Zhong ◽  
S.-X. Cheng
Keyword(s):  
Neural Networks ◽  
Time Varying ◽  
Chaotic Neural Networks ◽  
Scaling Parameter ◽  
Transiently Chaotic Neural Networks

SYNCHRONIZATION IN AN ARRAY OF HYBRID COUPLED NEURAL NETWORKS WITH MODE-DEPENDENT MIXED DELAYS AND MARKOVIAN SWITCHING

2009 ◽  
Vol 23 (09) ◽  
pp. 1171-1187 ◽  
Author(s):  
YANG TANG ◽  
RUNHE QIU ◽  
JIAN-AN FANG
Keyword(s):  
Neural Networks ◽  
Transition Probability ◽  
Distributed Delay ◽  
Mode Switching ◽  
Mixed Delays ◽  
Time Varying ◽  
Chaotic Neural Networks ◽  
Coupled Neural Networks ◽  
Hybrid Coupling ◽  
Coupling Time

In this letter, a general model of an array of N linearly coupled chaotic neural networks with hybrid coupling is proposed, which is composed of constant coupling, time-varying delay coupling and distributed delay coupling. The complex network jumps from one mode to another according to a Markovian chain with known transition probability. Both the coupling time-varying delays and the coupling distributed delays terms are mode-dependent. By the adaptive feedback technique, several sufficient criteria have been proposed to ensure the synchronization in an array of jump chaotic neural networks with mode-dependent hybrid coupling and mixed delays in mean square. Finally, numerical simulations illustrated by mode switching between two complex networks of different structure dependent on mode switching verify the effectiveness of the proposed results.

Adaptive Synchronization in Unknown Stochastic Chaotic Neural Networks with Mixed Time-Varying Delays

2011 ◽  
pp. 289-313
Author(s):  
Jian-an Fang ◽  
Yang Tang
Keyword(s):  
Neural Networks ◽  
Sufficient Conditions ◽  
Stochastic Perturbation ◽  
Adaptive Synchronization ◽  
Output Coupling ◽  
Time Varying ◽  
Connection Weight ◽  
Chaotic Neural Networks ◽  
Simulation Results ◽  
Feedback Techniques

Neural networks (NNs) have been useful in many fields, such as pattern recognition, image processing etc. Recently, synchronization of chaotic neural networks (CNNs) has drawn increasing attention due to the high security of neural networks. In this chapter, the problem of synchronization and parameter identification for a class of chaotic neural networks with stochastic perturbation via state and output coupling, which involve both the discrete and distributed time-varying delays has been investigated. Using adaptive feedback techniques, several sufficient conditions have been derived to ensure the synchronization of stochastic chaotic neural networks. Moreover, all the connection weight matrices can be estimated while the lag synchronization and complete synchronization is achieved in mean square at the same time. The corresponding simulation results are given to show the effectiveness of the proposed method.

Improved Results on Adaptive Control Approach for Projective Synchronization of Neural Networks with Time-Varying Delay

2019 ◽  
Vol 20 (6) ◽  
pp. 623-631 ◽  
Author(s):  
Abdujelil Abdurahman ◽  
Malika Sader ◽  
Haijun Jiang
Keyword(s):  
Neural Networks ◽  
Functional Method ◽  
Mean Value ◽  
Projective Synchronization ◽  
Mean Value Theorem ◽  
Time Varying ◽  
Chaotic Neural Networks ◽  
Control Approach ◽  
Time Varying Delay ◽  
Varying Delay

AbstractCompared to other types of synchronization such as complete synchronization and lag synchronization, there is a unique advantage in projective synchronization since it can greatly improve the security of communication. In this paper, the projective synchronization problem of a class of chaotic neural networks with time-varying delay is investigated via designing a novel adaptive controller. Some simple and useful criteria are derived by employing Lyapunov functional method and Lagrange mean value theorem. Finally, an example and its numerical simulations are given to demonstrate the effectiveness of the proposed control schemes. It is worth to mention that the designed controller in this paper dos not require any knowledge about the activation functions, which can be seen the main novelty of the paper.

Sign in / Sign up

Export Citation Format

Share Document