Knowledge processing system using multi-module associative memory

Author

Hattori, Motonobu

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Yamanashi Univ., Kofu, Japan

Volume

1

fYear

1998

fDate

4-8 May 1998

Firstpage

531

Abstract

A knowledge processing system using multi-module associative memory for many-to-many associations (MMA)² is proposed and simulated. In order to improve the fault tolerant performance, we employ Hopfield associative memories in the (MMA)². Then the (MMA) ² is applied to knowledge processing in which the knowledge is represented in a form of semantic network. The features of the proposed (MMA)² are: 1) it can deal with characteristics inheritance, exception processing and plural queries in knowledge processing; 2) it is robust for noisy inputs; and 3) it can guarantee the recall of all training data

Keywords

Hopfield neural nets; content-addressable storage; exception handling; fault tolerant computing; inheritance; knowledge based systems; semantic networks; Hopfield associative memories; characteristics inheritance; exception processing; fault tolerance; knowledge processing system; knowledge representation; many-to-many associations; multiple module associative memory; semantic network; Associative memory; Biological neural networks; Computational modeling; Computer simulation; Fault tolerance; Hebbian theory; Humans; Knowledge engineering; Robustness; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.682323

Filename

682323