Performance enhancement using nonlinear preprocessing

被引:7
作者
Chow, T
Leung, CT
机构
[1] Department of Electronic Engineering, City University of Hong Kong, Kowloon
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1996年 / 7卷 / 04期
关键词
D O I
10.1109/72.508947
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This letter describes a nonlinear preprocessing method to enhance the output performance of a network, The introduction of the nonlinear preprocessing method redistributes the distributions of input and output vectors, and makes the input and output variables more ''orthogonal'' that results in facilitating the network optimization, In some of the examples, this nonlinear preprocessing technique enables test set error to be enormously reduced by a magnitude of 98%, Three applications of time-series predictions applied to evaluate the performance of the proposed method are presented.
引用
收藏
页码:1039 / 1042
页数:4
相关论文
共 8 条
[1]   APPROXIMATIONS OF CONTINUOUS FUNCTIONALS BY NEURAL NETWORKS WITH APPLICATION TO DYNAMIC-SYSTEMS [J].
CHEN, TP ;
CHEN, H .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (06) :910-918
[2]  
CHOW TWS, 1995, P EUR S ART NEUR NET, P327
[3]  
HUBEL DH, 1979, SCI AM, V241, P150, DOI 10.1038/scientificamerican0979-150
[4]  
JOHNSON RA, 1982, APPLIED MULTIVARIATE
[5]   OSCILLATION AND CHAOS IN PHYSIOLOGICAL CONTROL-SYSTEMS [J].
MACKEY, MC ;
GLASS, L .
SCIENCE, 1977, 197 (4300) :287-288
[6]   EFFECT OF NONLINEAR TRANSFORMATIONS ON CORRELATION BETWEEN WEIGHTED SUMS IN MULTILAYER PERCEPTRONS [J].
OH, SH ;
LEE, YJ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (03) :508-510
[7]  
XUE Q, P IJCNN 90 WASH DC, V1, P739
[8]   EXTENDED BACKPROPAGATION ALGORITHM [J].
YAM, YF ;
CHOW, TWS .
ELECTRONICS LETTERS, 1993, 29 (19) :1701-1702