Title :
Optimisation of the performance of neural network based pattern recognition classifiers with distributed systems
Author :
Turkoglu, Ibrahim ; ARSLAN, Ahmet
Author_Institution :
Dept. of Electron. & Comput. Educ., Firat Univ., Elazig, Turkey
Abstract :
In this study, a new algorithm with distributed systems is proposed in order to optimise the structure of the classifiers, which have great importance in pattern recognition. The algorithm is applied to a multilayer neural network classifier, which uses the rule of backpropagation learning. The long process period is shortened and expected high operation speed is achieved in pattern recognition by minimizing the hardware realization of the classifier
Keywords :
backpropagation; distributed algorithms; multilayer perceptrons; pattern classification; performance evaluation; backpropagation learning; distributed systems; multilayer neural network classifier; pattern recognition classifiers; performance evaluation; Computer networks; Concurrent computing; Distributed computing; High performance computing; Multi-layer neural network; Neural networks; Pattern recognition; Physics computing; Power engineering computing; Power system reliability;
Conference_Titel :
Parallel and Distributed Systems, 2001. ICPADS 2001. Proceedings. Eighth International Conference on
Conference_Location :
Kyongju City
Print_ISBN :
0-7695-1153-8
DOI :
10.1109/ICPADS.2001.934843
