Title :
Learning optimal fuzzy rules using simulated annealing
Author :
Dickerson, Julie A.
Author_Institution :
Dept. of Electr. Eng. & Comput. Eng., Iowa State Univ., Ames, IA, USA
Abstract :
Fuzzy systems can uniformly approximate continuous functions, but the number of rules increases geometrically with system dimension. Fast simulated annealing that uses alpha stable generating functions to search locally and tunnel through space can solve large optimization problems. Generating functions with alpha values less than 1 can find the optimal fuzzy rules that approximate a function. The thick tails of these distributions help the annealing algorithm quickly search the solution space. This method can find the fuzzy rules for one and two input fuzzy systems
Keywords :
Gaussian distribution; fuzzy logic; simulated annealing; state-space methods; alpha stable generating functions; annealing algorithm; continuous functions; large optimization problems; optimal fuzzy rules; simulated annealing; solution space; system dimension; Additives; Computational modeling; Cooling; Fuzzy sets; Fuzzy systems; Gaussian distribution; Least squares approximation; Mesh generation; Probability distribution; Simulated annealing;
Conference_Titel :
Circuits and Systems, 1996., IEEE 39th Midwest symposium on
Conference_Location :
Ames, IA
Print_ISBN :
0-7803-3636-4
DOI :
10.1109/MWSCAS.1996.587782
