On-line learning in recurrent neural networks using nonlinear Kalman filters

被引：0

作者：

Todorovic, B ^{[1
]}

Stankovic, M ^{[1
]}

Moraga, C ^{[1
]}

机构：

[1] Univ Nish, Fac Occupat Safety, YU-18000 Nish, Serbia Monteneg, Yugoslavia

来源：

PROCEEDINGS OF THE 3RD IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY | 2003年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The extended Kalman filter has been successfully applied to the feedforward and the recurrent neural network training. Recently introduced derivative-free filters (Unscented Kalman Filter and Divided Difference Filter) outperform the extended Kalman filter in nonlinear state estimation. In the parameter estimation of the feedforward neural networks UKF and DDF are comparable or slightly better than EKF with a significant advantage that they do not demand calculation of the neural network Jacobian. In this paper, we consider the application Of EKF, UKF and DDF to the recurrent neural network training. The class of non-linear autoregressive recurrent neural networks with exogenous inputs is chosen as a basic architecture due to its powerful representational capabilities.

引用

页码：802 / 805

页数：4

共 50 条

[1] An on-line learning algorithm for recurrent neural networks using variational methods
Oh, WG
Suh, BS
[J]. 40TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2, 1998, : 659 - 662
[2] On-line learning algorithms for locally recurrent neural networks
Campolucci, P
Uncini, A
Piazza, F
Rao, BD
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (02): : 253 - 271
[3] LEARNING ALGORITHMS FOR NEURAL NETWORKS WITH THE KALMAN FILTERS
WATANABE, K
TZAFESTAS, SG
[J]. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 1990, 3 (04) : 305 - 319
[4] Parallel nonlinear adaptive digital filters using recurrent neural networks
Cao, JT
Yahagi, T
[J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1997, 80 (12): : 91 - 101
[5] Parallel nonlinear adaptive digital filters using recurrent neural networks
Cao, JT
Yahagi, T
[J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1997, 80 (03): : 83 - 93
[6] Targeted on-line modeling for an extended Kalman filter using artificial neural networks
Stubberud, SC
Owen, MW
[J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1019 - 1023
[7] On-line Gauss-Newton-based learning for fully recurrent neural networks
Vartak, A. A.
Georgiopoulos, M.
Anagnostopoulos, G. C.
[J]. NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2005, 63 (5-7) : E867 - E876
[8] On-line reinforcement learning using cascade constructive neural networks
Vamplew, P
Ollington, R
[J]. KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS, 2005, 3683 : 562 - 568
[9] On-line learning of robot arm impedance using neural networks
Tanaka, Y
Tsuji, T
[J]. IEEE ROBIO 2004: Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2004, : 941 - 946
[10] On-line learning of robot arm impedance using neural networks
Tsuji, T
Tanaka, Y
[J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2005, 52 (04) : 257 - 271

← 1 2 3 4 5 →