Justification-based belief maintenance using neural networks

Author

Gray, Michael A.

Author_Institution

American Univ., Washington, DC, USA

Volume

4

fYear

2000

fDate

2000

Firstpage

2515

Abstract

An implementation of justification-based belief maintenance using a Hopfield network has been proposed for relabeling belief graphs during belief maintenance. The paper analyzes the theoretical foundation of this work and discusses the source of representational and stability problems found in this system (called the Hopfield RMS). It extends that work by analyzing the advantages of a bidirectional associative memory and shows that the BAM is preferable to the Hopfield network for implementing justification based reason maintenance in intelligent agent belief systems

Keywords

Hopfield neural nets; belief maintenance; belief networks; content-addressable storage; software agents; BAM; Hopfield RMS; Hopfield network; belief graph relabeling; bidirectional associative memory; intelligent agent belief systems; justification based belief maintenance; justification based reason maintenance; neural networks; stability problems; Artificial neural networks; Associative memory; Computer networks; Decision making; Heart; Intelligent agent; Labeling; Magnesium compounds; Neural networks; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2000 IEEE International Conference on

Conference_Location

Nashville, TN

ISSN

1062-922X

Print_ISBN

0-7803-6583-6

Type

conf

DOI

10.1109/ICSMC.2000.884371

Filename

884371