THE UD RLS ALGORITHM FOR TRAINING FEEDFORWARD NEURAL NETWORKS

被引：0

作者：

Bilski, Jaroslaw ^{[1
]}

机构：

[1] Czestochowa Tech Univ, Dept Comp Engn, Ul Armii Krajowej 36, PL-42200 Czestochowa, Poland

来源：

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE | 2005年 / 15卷 / 01期

关键词：

neural networks; learning algorithms; recursive least squares method; UD factorization;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A new algorithm for training feedforward multilayer neural networks is proposed. It is based on recursive least squares procedures and U-D factorization, which is a well-known technique in filter theory. It will be shown that due to the U-D factorization method, our algorithm requires fewer computations than the classical RLS applied to feedforward multilayer neural network training.

引用

页码：115 / 123

页数：9

共 50 条

[21] A tabu search algorithm for the training of neural networks
Dengiz, B.
Alabas-Uslu, C.
Dengiz, O.
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2009, 60 (02) : 282 - 291
[22] A robust evolutionary algorithm for training neural networks
Yang, JM
Kao, CY
NEURAL COMPUTING & APPLICATIONS, 2001, 10 (03): : 214 - 230
[23] A training algorithm for partial recurrent neural networks
Al-Faysale, MSM
Modelling and Simulation 2004, 2004, : 350 - 354
[24] Parallel training algorithm of BP neural networks
Li, J
Li, YX
Xu, JW
Zhang, JB
PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 872 - 876
[25] Training Neural Networks with Krill Herd Algorithm
Kowalski, Piotr A.
Lukasik, Szymon
NEURAL PROCESSING LETTERS, 2016, 44 (01) : 5 - 17
[26] Feedforward neural networks using RPROP algorithm and its application in system identification
Zhou, LR
Han, P
Jiao, SM
Lin, BH
2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, 2002, : 2041 - 2044
[27] A novel learning algorithm of single-hidden-layer feedforward neural networks
Dong-Mei Pu
Da-Qi Gao
Tong Ruan
Yu-Bo Yuan
Neural Computing and Applications, 2017, 28 : 719 - 726
[28] A novel learning algorithm of single-hidden-layer feedforward neural networks
Pu, Dong-Mei
Gao, Da-Qi
Ruan, Tong
Yuan, Yu-Bo
NEURAL COMPUTING & APPLICATIONS, 2017, 28 : S719 - S726
[29] An efficient global algorithm for supervised training of neural networks
Shukla, KK
Raghunath
COMPUTERS & ELECTRICAL ENGINEERING, 1999, 25 (03) : 193 - 216
[30] Physically enhanced training for modeling rate-independent plasticity with feedforward neural networks
Patrick Weber
Werner Wagner
Steffen Freitag
Computational Mechanics, 2023, 72 : 827 - 857

← 1 2 3 4 5 →