標題: A PARALLEL GENETIC/NEURAL NETWORK LEARNING ALGORITHM FOR MIMD SHARED-MEMORY MACHINES
作者: HUNG, SL
ADELI, H
土木工程學系
Department of Civil Engineering
公開日期: 1-Nov-1994
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.
URI: http://dx.doi.org/10.1109/72.329686
http://hdl.handle.net/11536/2251
ISSN: 1045-9227
DOI: 10.1109/72.329686
期刊: IEEE TRANSACTIONS ON NEURAL NETWORKS
Volume: 5
Issue: 6
起始頁: 900
結束頁: 909
Appears in Collections:Articles


Files in This Item:

  1. A1994PQ76300004.pdf