Procedural knowledge processing based on area representation using a neural network

Author

Fujinaga, Seiya ; Hagiwara, Masafumi

Author_Institution

Dept. of Electr. Eng., Keio Univ., Yokohama, Japan

Volume

5

fYear

1997

fDate

12-15 Oct 1997

Firstpage

4519

Abstract

In this paper, a neural network is proposed which can deal with procedural knowledge based on area representation. The area representation expresses information by a group of neurons. Since it can be considered as a combination of localized representation and distributed representation, it has many advantages such as robustness, high efficiency for information representation, potential ability to treat similarity of data and so on. The proposed network based on area representation is constructed to store and recall procedural knowledge. We performed various kinds of computer simulations to examine the validity and effectiveness of the proposed network

Keywords

knowledge representation; learning (artificial intelligence); neural nets; performance evaluation; area representation; computer simulations; data similarity; distributed representation; high efficiency; information representation; knowledge representation; learning; localized representation; neural network; neurons; procedural knowledge processing; robustness; Artificial intelligence; Biological neural networks; Computer simulation; Humans; Intelligent networks; Intelligent systems; Knowledge representation; Neural networks; Neurons; Noise robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on

Conference_Location

Orlando, FL

ISSN

1062-922X

Print_ISBN

0-7803-4053-1

Type

conf

DOI

10.1109/ICSMC.1997.637583

Filename

637583