Symbolic Deductive Reasoning using Connectionist Models

Computer Science Journal of Moldova

Dan Galea¹  Florin Leon¹  Mihai Horia Zaharia¹ 

[1] Department of Automatic Control and Computer EngineeringTechnical University "Gh. Asachi", Iasi;

关键词: Artificial intelligence;    cognitive agents;    schemata;    knowledge representation;    deductive reasoning;    neural networks;   

DOI  :  

来源: DOAJ

【 摘 要 】

In this paper, we try to combine the possibility of symbolic deductive reasoning with the learning capability of the connectionist models. We introduce several algorithms for learning relations between concepts and finding paths in a transitive manner between learned concepts. An application that implements the proposed model is described and a number of case studies are presented.

【 授权许可】

Unknown