Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Strategic Study of CAE >> 2001, Volume 3, Issue 4

Learning and Applications of Procedure Neural Networks

1.Beijing Institute of System Engineering, Beijing 100101, China

2.Dept, of Computer Science, Daqing Petroleum Institute, Anda, Heilongjiang 151400, China

Funding project:“九七三”国家重点发展资助项目(G1999032705) Received: 2000-10-31 Revised: 2001-01-11 Available online: 2001-04-20

Next Previous

Abstract

This paper deals with learning algorithms for procedure neural networks (PNN) and its applications in aggregation chemical reaction and seepage test in oil geology. Weight bases selection rules and pattern curve standard problems are also discussed. These examples show that PNN have extensive applications.

Figures

图1

图2

图3

图4

References

[ 1 ] Hecht NielsenR Theoryofthebackpropagationneuralnetwork [A] ProceedingsofInternationalJointConfer enceonofNeuralNetworks [C] 1989, 1:5 93~ 5 99

[ 2 ] CybenkoG Approximationbysuperpositionofasig moidfunction [J] MathematicsofControl, SignalsandSystems, 1989, 2 :30 3~ 314 link1

[ 3 ] HornikK , StinchcombeM , WhiteH Multilayerfeed forwordnetworksareuniversalapproximators[J] Neu ralNetworks , 1989, 2 :35 9~ 36 6

[ 4 ] FunahashiK Ontheapproximaterealizationofcontin uousmappingsbyneuralnetworks [J] NeuralNet works, 1989, 2 :183~ 192

[ 5 ] ZhangLiI, TaoHuizhongW , HoltCE , etal Acriti calwindowforcooperationandcompetitionamongde velopingretinotectalsynapses [J] Nature , 1998, 395 :37~ 44

[ 6 ] 何新贵 , 梁久祯 过程神经元网络若干理论问题 [J].中国工程科学 , 2 0 0 0 , 2 (12 ) :40~ 44 link1

Related Research