Existence and global attractability of almost periodic solution for competitive neural networks with time-varying delays and different time scales

Authors:
Wentong Liao;Linshan Wang
Affiliations:
Department of Mathematics, Ocean University of China, Qingdao, People’s Republic of China;Department of Mathematics, Ocean University of China, Qingdao, People’s Republic of China
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Year:
2006

Citing 4
Cited 1

Learning continuous trajectories in recurrent neural networks with time-dependent weights

IEEE Transactions on Neural Networks
Stable dynamic backpropagation learning in recurrent neural networks

IEEE Transactions on Neural Networks
Robust local stability of multilayer recurrent neural networks

IEEE Transactions on Neural Networks
Global exponential stability of competitive neural networks with different time scales

IEEE Transactions on Neural Networks

Existence of periodic solution for competitive neural networks with time-varying and distributed delays on time scales

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The dynamics of cortical cognitive maps developed by self-organization must include the aspects of long and short-term memory. The behavior of such a neural network is characterized by an equation of neural activity as a fast phenomenon and an equation of synaptic modification as a slow part of the neural system, besides,this model bases on unsupervised synaptic learning algorithm. Considered the effect of time delays, we prove the existence, uniqueness and global attraction of the almost periodic solution by using fixed theorem and Variation-of-constants formula.