Simulated Annealing Based Learning Approach for the Design of Cascade Architectures of Fuzzy Neural Networks
This paper is concerned with the optimization method of the cascade architectures of fuzzy neural networks. The structure of the network that deals with a selection of a subset of input variables and their distribution across the individual logic processors (LPs) is optimized with the use of genetic algorithms (GA). We discuss random signal-based learning employing simulated annealing (SARSL), a local search technique, aimed at further refinement of the connections of the neurons (GA-SARSL). A standard data set is discussed with respect to the performance of the constructed networks and their interpretability.
KeywordsGenetic Algorithm Fuzzy Neural Network Local Search Technique Genetic Algorithm Mode Logic Processor
Unable to display preview. Download preview PDF.
- 3.Michalewicz, Z.: Genetic Algorithm + Data Structures = Evolution Programs, 3rd edn. Springer, Berlin (1996)Google Scholar
- 4.Han, C.W., Park, J.I.: Design of a Fuzzy Controller using Random Signal-based Learning Employing Simulated Annealing. In: Proc. of the 39th IEEE Conference on Decision and Control, pp. 396–397 (2000)Google Scholar