Median radial basis function neural network

被引:101
作者
Bors, AG
Pitas, I
机构
[1] Department of Informatics, University of Thessaloniki, Thessaloniki
来源
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1996年 / 7卷 / 06期
关键词
D O I
10.1109/72.548164
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Radial basis functions (RBF's) consist of a two-layer neural network, where each hidden unit implements a kernel function, Each kernel is associated with an activation region from the input space and its output is fed to an output unit, In order to find the parameters of a neural network which embeds this structure we take into consideration two different statistical approaches, The first approach uses classical estimation in the learning stage and it is based on the learning vector quantization algorithm and its second-order statistics extension, After the presentation of this approach,we introduce the median radial basis function (MRBF) algorithm based on robust estimation of the hidden unit parameters. The proposed algorithm employs the marginal median for kernel location estimation and the median of the absolute deviations for the scale parameter estimation, A histogram-based fast implementation is provided for the MRBF algorithm, The theoretical performance of the two training algorithms is comparatively evaluated when estimating the network weights, The network is applied in pattern classification problems and in optical flow segmentation.
引用
收藏
页码:1351 / 1364
页数:14
相关论文
共 38 条
[1]  
Bors A. G., 1994, Digital Signal Processing, V4, P173, DOI 10.1006/dspr.1994.1016
[2]  
BORS AG, 1995, P IEEE WKSHP NONL SI, P702
[3]  
BORS AG, 1994, P IEEE WKSHP NEUR NE, P105
[4]  
Broomhead D. S., 1988, Complex Systems, V2, P321
[5]  
CHANG MM, 1993, P IEEE INT C AC SPEE
[6]   ORTHOGONAL LEAST-SQUARES LEARNING ALGORITHM FOR RADIAL BASIS FUNCTION NETWORKS [J].
CHEN, S ;
COWAN, CFN ;
GRANT, PM .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (02) :302-309
[7]   A CLUSTERING TECHNIQUE FOR DIGITAL-COMMUNICATIONS CHANNEL EQUALIZATION USING RADIAL BASIS FUNCTION NETWORKS [J].
CHEN, S ;
MULGREW, B ;
GRANT, PM .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (04) :570-579
[8]   OVERCOMING COCHANNNEL INTERFERENCE USING AN ADAPTIVE RADIAL BASIS FUNCTION EQUALIZER [J].
CHEN, S ;
MULGREW, B .
SIGNAL PROCESSING, 1992, 28 (01) :91-107
[9]  
Gersho A., 1992, Vector quantization and signal compression
[10]   Layered Neural Networks with Gaussian Hidden Units as Universal Approximations [J].
Hartman, Eric J. ;
Keeler, James D. ;
Kowalski, Jacek M. .
NEURAL COMPUTATION, 1990, 2 (02) :210-215