A novel neural network for associative memory via dynamical systems

K. L. Mak; J. G. Peng; Z. B. Xu; K. F. C. Yiu

doi:10.3934/dcdsb.2006.6.573

Article Contents

2006, Volume 6, Issue 3: 573-590. Doi: 10.3934/dcdsb.2006.6.573

This issue Previous Article Bifurcations in a discrete time Lotka-Volterra predator-prey system Next Article Dynamic bifurcation theory of Rayleigh-Bénard convection with infinite Prandtl number

A novel neural network for associative memory via dynamical systems

1.
Department of Industrial and Manufacturing Systems Engineering, The University of Hong Kong, Pokfulam Road, Hong Kong
2.
Institute for Information and System Science, Faculty of Science, Xi'an Jiaotong University, Xi'an 710049

Received: May 31, 2005

Revised: November 30, 2005

Published: April 2007

Abstract Related Papers Cited by

Abstract

This paper proposes a novel neural network model for associative memory using dynamical systems. The proposed model is based on synthesizing the external input vector, which is different from the conventional approach where the design is based on synthesizing the connection matrix. It is shown that this new neural network (a) stores the desired prototype patterns as asymptotically stable equilibrium points, (b) has no spurious states, and (c) has learning and forgetting capabilities. Moreover, new learning and forgetting algorithms are also developed via a novel operation on the matrix space. Numerical examples are presented to illustrate the effectiveness of the proposed neural network for associative memory. Indeed, results of simulation experiments demonstrate that the neural network is effective and can be implemented easily.

Keywords:

Mathematics Subject Classification: 92B20, 37C75, 68T05.

Citation:

Article Metrics

HTML views() PDF downloads(81) Cited by(0)

A novel neural network for associative memory via dynamical systems

Abstract

Access History

Article Metrics

Access History

Other Articles By Authors

Catalog

A novel neural network for associative memory via dynamical systems

Abstract

Access History

SHARE

Article Metrics

Access History

Other Articles By Authors

Catalog

Export File

Citation

Format

Content