Probabilistic self-organizing map and radial basis function networks

被引:33
作者
Anouar, F
Badran, F
Thiria, S
机构
[1] Conservatoire Natl Arts & Metiers, CEDRIC, F-750003 Paris, France
[2] Univ Paris 06, Lab Oceanog & Climatol, LODYC, F-75005 Paris, France
关键词
self-organizing map; dynamic clusters; likelihood; radial basis function; regression;
D O I
10.1016/S0925-2312(98)00026-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose in this paper a new learning algorithm probabilistic self-organizing map (PRSOM) using a probabilistic formalism for topological maps. This algorithm approximates the density distribution of the input set with a mixture of normal distributions. The unsupervised learning is based on the dynamic clusters principle and optimizes the likelihood function. A supervised version of this algorithm based on radial basis functions (RBF) is proposed. In order to validate the theoretical approach, we achieve regression tasks on simulated and real data using the PRSOM algorithm. Moreover, our results are compared with normalized Gaussian basis functions (NGBF) algorithm. (C) 1998 Published by Elsevier Science B.V. All rights reserved.
引用
收藏
页码:83 / 96
页数:14
相关论文
共 17 条
[1]  
BENAIM M, 1994, NEURAL COMPUT, V6
[2]  
BISHOP C, GTM PRINCIPLED ALTER
[3]  
Bishop C. M., 1995, NEURAL NETWORKS PATT
[4]  
CELEUX G, 1984, RECONNAISSANCE MELAN
[5]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[6]  
Diday E., 1976, DIGITAL PATTERN CLAS
[7]   GROWING CELL STRUCTURES - A SELF-ORGANIZING NETWORK FOR UNSUPERVISED AND SUPERVISED LEARNING [J].
FRITZKE, B .
NEURAL NETWORKS, 1994, 7 (09) :1441-1460
[8]  
HARTMAN E, 1990, NEURAL COMPUT, V2
[9]  
Kohonen T., 1994, SELF ORGANIZING MAPS
[10]  
LUTTREL SP, 1994, NEURAL COMPUT, V6