Neurocomputations in relational systems
- 1 March 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13 (3) , 289-297
- https://doi.org/10.1109/34.75517
Abstract
Strong analogies between relational structures involving some composition operators and a certain class of neural networks are described. The problem of learning the connections of the structure is addressed, and relevant learning procedures are proposed. An optimized performance index which has a strong logical flavor is proposed. Some significant implementation details are studied. Numerical examples illustrate various schemes of learning in relational structures of different levels of complexity.Keywords
This publication has 12 references indexed in Scilit:
- Direct and inverse problem in comparison of fuzzy dataFuzzy Sets and Systems, 1990
- A fuzzy cognitive structure for pattern recognitionPattern Recognition Letters, 1989
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Neocognitron: A neural network model for a mechanism of visual pattern recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1983
- A MODEL OF LEARNING BASED ON FUZZY INFORMATIONKybernetes, 1977
- Resolution of composite fuzzy relation equationsInformation and Control, 1976
- A Search Technique of Control Rod Pattern for Smoothing Core Power Distributions by Fuzzy AutomatonJournal of Nuclear Science and Technology, 1973
- Outline of a New Approach to the Analysis of Complex Systems and Decision ProcessesIEEE Transactions on Systems, Man, and Cybernetics, 1973
- A Formulation of Fuzzy Automata and Its Application as a Model of Learning SystemsIEEE Transactions on Systems Science and Cybernetics, 1969
- Statistical MetricsProceedings of the National Academy of Sciences, 1942