FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling

被引：124

作者：

Back, A. D. ^{[1
]}

Tsoi, A. C. ^{[1
]}

机构：

[1] Univ Queensland, Dept Elect Engn, Brisbane, Qld 4072, Australia

来源：

NEURAL COMPUTATION | 1991年 / 3卷 / 03期

关键词：

D O I：

10.1162/neco.1991.3.3.375

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new neural network architecture involving either local feedforward global feedforward, and/or local recurrent global feedforward structure is proposed. A learning rule minimizing a mean square error criterion is derived. The performance of this algorithm (local recurrent global feedforward architecture) is compared with a local-feedforward global-feedforward architecture. It is shown that the local-recurrent global-feedforward model performs better than the local-feedforward global-feedforward model.

引用

页码：375 / 385

页数：11