Title :
Fuzzy parameter adaptation in optimization: some neural net training examples
Author :
Arabshahi, Payman ; Choi, Jai J. ; Marks, Robert J., II ; Caudell, Thomas P.
Author_Institution :
Alabama Univ., Huntsville, AL, USA
Abstract :
Parameters of certain neural net training algorithms and classification procedures are often chosen or adapted using heuristics that contain fuzzy descriptors. Such heuristics, quantified into a fuzzy inference engine, can take the human out of the loop and provide for faster convergence or improved performance. Other applications, outside of neural nets, are also possible
Keywords :
ART neural nets; adaptive systems; fuzzy logic; fuzzy neural nets; learning (artificial intelligence); optimisation; classification procedures; convergence; fuzzy descriptors; fuzzy inference engine; fuzzy parameter adaptation; heuristics; neural net training algorithms; optimization; parameter selection; performance; Artificial neural networks; Backpropagation algorithms; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Humans; Neural networks; Subspace constraints;
Journal_Title :
Computational Science & Engineering, IEEE
