HIERARCHICAL NEURAL NETWORKS FOR TIME-SERIES ANALYSIS AND CONTROL

被引：7

作者：

FROHLINGHAUS, T

WEICHERT, A

RUJAN, P

机构：

[1] CARL VON OSSIETZKY UNIV,FACHBEREICH INFORMAT 10,D-26111 OLDENBURG,GERMANY

[2] CARL VON OSSIETZKY UNIV,FACHBEREICH PHYS 8,D-26111 OLDENBURG,GERMANY

来源：

NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1994年 / 5卷 / 01期

关键词：

D O I：

10.1088/0954-898X/5/1/007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A hierarchical network of neurons with local receptive fields is constructed by using a mixture of clustering and supervised learning strategies. The network's performance is enhanced by built-in importance sampling and by its multiscale organization in both time and phase space domains. The method is tested on predicting chaotic time-series and on balancing a physical pendulum.

引用

页码：101 / 116

页数：16

共 27 条

[1]

[Anonymous], 1964, SUNSPOTS

[2] MULTIDIMENSIONAL BINARY SEARCH TREES USED FOR ASSOCIATIVE SEARCHING [J].