A Parallel Genetic/Neural Network Learning Algorithm for MIMD Shared Memory Machines

Shih-Lin Hung, H. Adeli

研究成果: Article同行評審

123 引文 斯高帕斯(Scopus)

摘要

A new algorithm is presented for training of multilayer feedforward neural networks by integrating a genetic algorithm with an adaptive conjugate gradient neural network learning algorithm. The parallel hybrid learning algorithm has been implemented in C on an MIMD shared memory machine (Cray Y-MP8/864 supercomputer). It has been applied to two different domains, engineering design and image recognition. The performance of the algorithm has been evaluated by applying it to three examples. The superior convergence property of the parallel hybrid neural network learning algorithm presented in this paper is demonstrated.

原文English
頁(從 - 到)900-909
頁數10
期刊IEEE Transactions on Neural Networks
5
發行號6
DOIs
出版狀態Published - 1 1月 1994

指紋

深入研究「A Parallel Genetic/Neural Network Learning Algorithm for MIMD Shared Memory Machines」主題。共同形成了獨特的指紋。

引用此