Title :
Representing taxonomical hierarchy of knowledge by structured Boltzmann machine
Author :
Okuno, Taku ; Kakazu, Yukinori
Author_Institution :
Dept. of Precision Eng., Hokkaido Univ., Sapporo, Japan
fDate :
27 Jun-2 Jul 1994
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;
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
DOI :
10.1109/ICNN.1994.374509
