Representing taxonomical hierarchy of knowledge by structured Boltzmann machine

Author

Okuno, Taku ; Kakazu, Yukinori

Author_Institution

Dept. of Precision Eng., Hokkaido Univ., Sapporo, Japan

Volume

3

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

1498

Abstract

The Boltzmann machine for content-addressable memory is structured to explicitly deal with taxonomical hierarchy of learned concepts embedded in its weights. It is realized by iterating three processes: extracting a subnetwork which represents an abstract concept, replacing it with a unit, and generating new layer by connecting it with the subnetwork. By this architecture, constraints on such hierarchy embedded in knowledge can be utilized to process knowledge to some extent. Its effectiveness is demonstrated by computer simulations

Keywords

Boltzmann machines; content-addressable storage; iterative methods; knowledge representation; learning (artificial intelligence); neural nets; computer simulations; content-addressable memory; iteration; structured Boltzmann machine; subnetwork extraction; taxonomical knowledge hierarchy; Computer architecture; Computer simulation; Degradation; Hopfield neural networks; Humans; Joining processes; Knowledge engineering; Neural networks; Precision engineering; Tensile stress;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374509

Filename

374509