Fuzzy neural networks with reference neurons as pattern classifiers
- 1 January 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 3 (5) , 770-775
- https://doi.org/10.1109/72.159065
Abstract
A heterogeneous neural network consisting of logic neurons and realizing mappings in [0, 1] hypercubes is presented. The two kinds of neurons studied are utilized to perform matching functions (equality or reference neurons) and aggregation operations (aggregation neurons). All computations are driven by logic operations widely used in fuzzy set theory. The network is heterogeneous in its nature and includes two types of neurons organized into a structure detecting individual regions of patterns (using reference neurons) and combining them to yield a final classification decision.Keywords
This publication has 5 references indexed in Scilit:
- Neural networks and knowledge engineeringIEEE Transactions on Knowledge and Data Engineering, 1991
- Processing in relational structures: Fuzzy relational equationsFuzzy Sets and Systems, 1991
- Neurocomputations in relational systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Direct and inverse problem in comparison of fuzzy dataFuzzy Sets and Systems, 1990
- Vector quantization of images based upon the Kohonen self-organizing feature mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988