A novel continuous-time neural network for realizing associative memory

Author

Tao, Qing ; Fang, Tingjian ; Qiao, Hong

Author_Institution

Hefei Inst. of Intelligent Machines, Acad. Sinica, Hefei, China

Volume

12

Issue

2

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

418

Lastpage

423

Abstract

A novel neural network is proposed in this paper for realizing associative memory. The main advantage of the neural network is that each prototype pattern is stored if and only if as an asymptotically stable equilibrium point. Furthermore, the basin of attraction of each desired memory pattern is distributed reasonably (in the Hamming distance sense), and an equilibrium point that is not asymptotically stable is really the state that cannot be recognized. The proposed network also has a high storage as well as the capability of learning and forgetting, and all its components can be implemented. The network considered is a very simple linear system with a projection on a closed convex set spanned by the prototype patterns. The advanced performance of the proposed network is demonstrated by means of simulation of a numerical example

Keywords

asymptotic stability; content-addressable storage; neural nets; Hamming distance; associative memory realization; asymptotically stable equilibrium point; attraction basin; closed convex set; continuous-time neural network; forgetting; learning; linear system; prototype pattern storage; prototype patterns; Artificial neural networks; Associative memory; Hamming distance; Learning systems; Linear systems; Network synthesis; Neural networks; Numerical simulation; Pattern recognition; Prototypes;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.914536

Filename

914536