Stability analysis of discrete hopfield neural networks combined with small ones

Authors:
Weigen Wu;Jimin Yuan;Jun Li;Qianrong Tan;Xing Yin
Affiliations:
School of Computer Science and Technology, Pan Zhi Hua University, Panzhihua, China;School of Computer Science and Technology, Pan Zhi Hua University, Panzhihua, China;School of Computer Science and Technology, Pan Zhi Hua University, Panzhihua, China;School of Computer Science and Technology, Pan Zhi Hua University, Panzhihua, China;School of Computer Science and Technology, Pan Zhi Hua University, Panzhihua, China
Venue:
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Year:
2010

Citing 5
Cited 0

Asymmetric Hopfield-type networks: theory and applications

Neural Networks
Letters: Stability analysis of a discrete Hopfield neural network with delay

Neurocomputing
Stability conditions for discrete neural networks in partial simultaneous updating mode

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Some efficient strategies for improving the eigenstructure method in synthesis of feedback neural networks

IEEE Transactions on Neural Networks
New stability conditions for Hopfield networks in partial simultaneous update mode

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The stability of Discrete Hopfield neural networks (DHNNs) is very important in various applications, but stability analysis of complex DHNNs is difficult However, stability analysis of simple and small DHNNs is easy to obtain In this paper, we study on the stability of DHNNs combined with two small ones that maybe have partially or completely different neurons, and consider the connected weights of different neurons And some new stability conditions of the DHNNs are obtained by studying the stability of small ones Those results provide the guided significance for designing a DHNNs and afford benefit for stability analysis of DHNNs The obtained results provide some theory bases of the application of DHNNs.