Title :
FSR-ARTMAP: a modified fuzzy ARTMAP with fuzzy signals and rules
Author :
Pham, D.T. ; Shankir, Y.M.A.
Author_Institution :
Syst. Eng. Div., Cardiff Univ., UK
Abstract :
Introduces a neural architecture termed the “Fuzzy Signals and Rules ARTMAP” (FSR-ARTMAP). It is a modified fuzzy ARTMAP for incremental supervised learning and multidimensional mapping using fuzzy signals. This neural architecture is able to process and store linguistic information in the form of fuzzy logic rules and membership functions for fuzzy inference. The FSR-ARTMAP architecture is composed of two similar “Fuzzy Signals and Rules ART” (FSR-ART) modules and a mapping field. FSR-ART is a modified version of fuzzy ART. The mapping field between the input and the output FSR-ART modules can be one-to-one, many-to-one or one-to-many
Keywords :
ART neural nets; fuzzy logic; fuzzy neural nets; inference mechanisms; learning (artificial intelligence); neural net architecture; FSR-ART modules; FSR-ARTMAP; fuzzy inference; fuzzy logic rules; fuzzy membership functions; fuzzy signals; incremental supervised learning; linguistic information; many-to-one mapping; mapping field; modified fuzzy ARTMAP; multidimensional mapping; neural architecture; one-to-many mapping; one-to-one mapping; Artificial neural networks; Backpropagation algorithms; Fuzzy logic; Fuzzy neural networks; Multidimensional systems; Neural networks; Signal mapping; Subspace constraints; Supervised learning; Systems engineering and theory;
Conference_Titel :
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-5871-6
DOI :
10.1109/ICONIP.1999.844001
