Knowledge-based connectionism for revising domain theories
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. 23 (1) , 173-182
- https://doi.org/10.1109/21.214775
Abstract
A knowledge-based connectionist model for machine learning referred to as KBCNN is presented. In the KBCNN learning model, useful domain attributes and concepts are first identified and linked in a way consistent with initial domain knowledge, and then the links are weighted properly so as to maintain the semantics. Hidden units and additional connections may be introduced into this initial connectionist structure as appropriate. Then, this primitive structure evolves to minimize empirical error. The KBCNN learning model allows the theory learned or revised to be translated into the symbolic rule-based language that describes the initial theory. Thus, a domain theory can be pushed onto the network, revised empirically over time, and decoded in symbolic form. The domain of molecular genetics is used to demonstrate the validity of the KBCNN learning model and its superiority over related learning methods.<>Keywords
This publication has 13 references indexed in Scilit:
- Estimation of generalization capability by combination of new information criterion and cross validationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Double backpropagation increasing generalization performancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Back-propagation learning in expert networksIEEE Transactions on Neural Networks, 1992
- Knowledge base refinement by backpropagationData & Knowledge Engineering, 1991
- Using Background Knowledge in Concept FormationPublished by Elsevier ,1991
- Mapping rule-based systems into neural architectureKnowledge-Based Systems, 1990
- Connectionist learning proceduresArtificial Intelligence, 1989
- Why are “What” and “Where” Processed by Separate Cortical Visual Systems? A Computational InvestigationJournal of Cognitive Neuroscience, 1989
- Connectionist expert systemsCommunications of the ACM, 1988
- Explanation-based generalization: A unifying viewMachine Learning, 1986