Resilient back propagation learning algorithm for recurrent fuzzy neural networks

被引：17

作者：

Mastorocostas, PA ^{[1
]}

机构：

[1] Technol & Educ Inst Serres, Dept Informat & Commun, Serres 62124, Greece

来源：

ELECTRONICS LETTERS | 2004年 / 40卷 / 01期

关键词：

D O I：

10.1049/el:20040052

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An efficient training method for recurrent fuzzy neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static neural networks, in order to be applied to dynamic systems. A comparative analysis with the standard back propagation through time is given, indicating the effectiveness of the proposed algorithm.

引用

页码：57 / 58

页数：2

共 5 条

[1] Empirical evaluation of the improved Rprop learning algorithms [J].

Igel, C ;

Hüsken, M .

NEUROCOMPUTING, 2003, 50 :105-123

[2] A recurrent self-organizing neural fuzzy inference network [J].

Juang, CF ;

Lin, CT .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (04) :828-845

[3] A recurrent fuzzy-neural model for dynamic system identification [J].

Mastorocostas, PA ;

Theocharis, JB .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2002, 32 (02) :176-190

[4] STEEPEST DESCENT ALGORITHMS FOR NEURAL-NETWORK CONTROLLERS AND FILTERS [J].

PICHE, SW .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :198-212

[5]

RIEDMILLER M, 1993, 1993 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, P586, DOI 10.1109/ICNN.1993.298623

← 1 →