Associative Semantic Memory Capable of Fast Inference on Conceptual Hierarchies

Qing MA  Hitoshi ISAHARA  

IEICE TRANSACTIONS on Information and Systems   Vol.E81-D   No.6   pp.572-583
Publication Date: 1998/06/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
adaptive associative memory,  pattern segmentation and recovery,  conceptual hierarchy,  inference,  computational effectiveness,  

Full Text: PDF(1.1MB)>>
Buy this Article

The adaptive associative memory proposed by Ma is used to construct a new model of semantic network, referred to as associative semantic memory (ASM). The main novelty is its computational effectiveness which is an important issue in knowledge representation; the ASM can do inference based on large conceptual hierarchies extremely fast-in time that does not increase with the size of conceptual hierarchies. This performance cannot be realized by any existing systems. In addition, ASM has a simple and easily understandable architecture and is flexible in the sense that modifying knowledge can easily be done using one-shot relearning and the generalization of knowledge is a basic system property. Theoretical analyses are given in general case to guarantee that ASM can flawlessly infer via pattern segmentation and recovery which are the two basic functions that the adaptive associative memory has.