MAXIMUM-ENTROPY, PSEUDOINVERSE TECHNIQUES, AND TIME-SERIES PREDICTIONS WITH LAYERED NETWORKS

被引:7
|
作者
DIAMBRA, L
PLASTINO, A
机构
[1] Departamento de Física, Universidad Nacional de la Plata, (1900) La Plata
来源
PHYSICAL REVIEW E | 1995年 / 52卷 / 04期
关键词
D O I
10.1103/PhysRevE.52.4557
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
A maximum-entropy-based method for the training of layered networks is presented. Our technique guarantees an errorless learning process for learnable mappings with just a minimum number of examples. The network is proposed for nonlinear systems prediction. Some numerical examples for chaotic time series are presented. The method can be considered to yield an alternative tool for feed-forward training.
引用
收藏
页码:4557 / 4560
页数:4
相关论文
共 50 条