Title :
Learning by means of free associative neurons
Author :
Raitz, Roberto T. ; Souza, J.A. ; Dandolini, G.A. ; Pacheco, Roberto C. S ; Martins, Alejandro ; Gauthier, Fernando A. ; Barcia, Ricardo M.
Author_Institution :
Graduate Program in Production Eng, Fed. Univ. of Santa Catarina, Florianopolis, Brazil
Abstract :
Introduces a new learning method: free associative neurons (FAN). FAN is composed of independent units with autonomous learning capabilities. The learning power of FAN is based on the association of its units and on the use of granularity for representing information. As a method for representing complex environments, FAN can be used in pattern recognition, classification and diagnosis. This paper is focused on the principles governing FAN. We also discuss some results and compare them to well-known artificial neural network algorithms
Keywords :
diagnostic reasoning; learning (artificial intelligence); neural nets; pattern recognition; FAN learning method; artificial neural network algorithms; autonomous learning capabilities; complex environments; diagnosis; free associative neurons; granularity; hybrid systems; independent units; information representation; pattern classification; pattern recognition; units association; Competitive intelligence; Computational intelligence; Humans; Intelligent networks; Learning systems; Neural networks; Neurons; Pattern recognition; Production engineering; Uncertainty;
Conference_Titel :
Fuzzy Information Processing Society, 1997. NAFIPS '97., 1997 Annual Meeting of the North American
Conference_Location :
Syracuse, NY
Print_ISBN :
0-7803-4078-7
DOI :
10.1109/NAFIPS.1997.624080
