Associative Semantic Memory Capable of Fast Inference on Conceptual Hierarchies

摘要

The adaptive associative memory proposed by Ma is used to construct a new model of semantic network, re- ferred to as associative semantic memory (ASM). The main nov- elty 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 perfor- mance 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.