A PARALLEL GENETIC/NEURAL NETWORK LEARNING ALGORITHM FOR MIMD SHARED-MEMORY MACHINES

被引：115

作者：

HUNG, SL ^{[1
]}

ADELI, H ^{[1
]}

机构：

[1] OHIO STATE UNIV,COLL ENGN,COLUMBUS,OH 43210

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1994年 / 5卷 / 06期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/72.329686

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

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.

引用

页码：900 / 909

页数：10

共 14 条

[1]

Adeli H., 1989, Microcomputers in Civil Engineering, V4, P247

[2]

ADELI H, 1990, JUL P INT NEUR NET C, P412

[3]

Adeli H., 1993, J AEROSPACE ENG, V6, P315, DOI [DOI 10.1061/(ASCE)0893-1321(1993)6:4(315), 10.1061/(asce)0893-1321(1993)6:4(315)]

[4]

[Anonymous], 1987, LEARNING INTERNAL RE

[5]

BELEW RK, 1990, CS90174 U CAL SAN DI

[6]

Davis L. E.., 1991, HDB GENETIC ALGORITH

[7]

Goldberg DE, 1989, GENETIC ALGORITHMS S

[8]

Hoffmeister F., 1991, Parallel Problem Solving from Nature. 1st Workshop, PPSN 1 Proceedings, P455, DOI 10.1007/BFb0029787

[9]

Hung S. L., 1991, Neurocomputing, V3, P3, DOI 10.1016/0925-2312(91)90016-5

[10] PARALLEL BACKPROPAGATION LEARNING ALGORITHMS ON CRAY Y-MP8/864 SUPERCOMPUTER [J].

HUNG, SL ;

ADELI, H .

NEUROCOMPUTING, 1993, 5 (06) :287-302

← 1 2 →