An on-line learning algorithm for recurrent neural networks using variational methods

被引：0

作者：

Oh, WG ^{[1
]}

Suh, BS ^{[1
]}

机构：

[1] Sunchon Natl Univ, Dept Comp & Commun Engn, Chonnam, South Korea

来源：

40TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2 | 1998年

关键词：

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：

In this paper, an on-line learning algorithm for recurrent neural networks(RNN) using optimal control and variational method is proposed. First, we obtain optimal weights given by a two-point boundary-value problem using the variational methods. And then the local gradient descent algorithm is derived such that on-line training is possible. This method is intended to be used on learning complex dynamic mappings between time-varing input-output data, Therefore it is useful for nonlinear control, identification, and signal processing applications of RNN. Simulation results for nonlinear plant identification are illustrated.

引用

页码：659 / 662

页数：4

共 50 条

[1] On-line learning in recurrent neural networks using nonlinear Kalman filters
Todorovic, B
Stankovic, M
Moraga, C
PROCEEDINGS OF THE 3RD IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2003, : 802 - 805
[2] On-line learning algorithms for locally recurrent neural networks
Campolucci, P
Uncini, A
Piazza, F
Rao, BD
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (02): : 253 - 271
[3] New on-line recursive learning algorithm for recurrent neural network
Wei, Wei
Zidonghua Xuebao/Acta Automatica Sinica, 1998, 24 (05): : 616 - 621
[4] New on-line recursive learning algorithm for recurrent neural network
Zhejiang Univ, Hangzhou, China
Ruan Jian Xue Bao, 4 (616-621):
[5] On-line Gauss-Newton-based learning for fully recurrent neural networks
Vartak, A. A.
Georgiopoulos, M.
Anagnostopoulos, G. C.
NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2005, 63 (5-7) : E867 - E876
[6] On-line learning of robot arm impedance using neural networks
Tanaka, Y
Tsuji, T
IEEE ROBIO 2004: Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2004, : 941 - 946
[7] On-line reinforcement learning using cascade constructive neural networks
Vamplew, P
Ollington, R
KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS, 2005, 3683 : 562 - 568
[8] On-line learning of robot arm impedance using neural networks
Tsuji, T
Tanaka, Y
ROBOTICS AND AUTONOMOUS SYSTEMS, 2005, 52 (04) : 257 - 271
[9] Stable Learning Algorithm Using Reducibility for Recurrent Neural Networks
Satoh, Seiya
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT VI, 2023, 14259 : 127 - 139
[10] On-line estimation of rotor resistance of an induction motor using recurrent neural networks
Mayaleh, S
Bayindir, NS
ELECTRONICS LETTERS, 1998, 34 (08) : 820 - 821

← 1 2 3 4 5 →