Combining Prior Symbolic Knowledge and Constructive Neural Network Learning
- 1 January 1993
- journal article
- research article
- Published by Taylor & Francis in Connection Science
- Vol. 5 (3-4) , 365-375
- https://doi.org/10.1080/09540099308915705
Abstract
The concepts of knowledge-based systems and machine learning are combined by integrating an expert system and a constructive neural networks learning algorithm. Two approaches are explored: embedding the expert system directly and converting the expert system rule base into a neural network. This initial system is then extended by constructively learning additional hidden units in a problem-specific manner. Experiments performed indicate that generalization of a combined system surpasses that of each system individually.Keywords
This publication has 8 references indexed in Scilit:
- Parallel and distributed systems for constructive neural network learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Neural net algorithms that learn in polynomial time from examples and queriesIEEE Transactions on Neural Networks, 1991
- Perceptron-based learning algorithmsIEEE Transactions on Neural Networks, 1990
- Learning in feedforward layered networks: the tiling algorithmJournal of Physics A: General Physics, 1989
- Neurocomputing, Volume 1Published by MIT Press ,1988
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Multidimensional binary search trees used for associative searchingCommunications of the ACM, 1975
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943