State Estimation and Tracking Problems: A Comparison Between Kalman Filter and Recurrent Neural Networks

2004 ◽  
pp. 275-281 ◽  
Author(s):  
S. Kumar Chenna ◽  
Yogesh Kr. Jain ◽  
Himanshu Kapoor ◽  
Raju S. Bapi ◽  
N. Yadaiah ◽  
...  
Keyword(s):  
Neural Networks ◽  
Kalman Filter ◽  
State Estimation ◽  
Recurrent Neural Networks

H∞ State Estimation of Memristor-based Recurrent Neural Networks with Mixed Delay

2019 ◽  
Author(s):  
Xiangxiang Wang ◽  
Yongbin Yu ◽  
Nijing Yang ◽  
Haowen Tang ◽  
Shouming Zhong ◽  
...  
Keyword(s):  
Neural Networks ◽  
State Estimation ◽  
Recurrent Neural Networks ◽  
Mixed Delay

State estimation of memristor-based recurrent neural networks with time-varying delays based on passivity theory

Complexity ◽  
2013 ◽  
Vol 19 (4) ◽  
pp. 32-43 ◽  
Author(s):  
R. Rakkiyappan ◽  
A. Chandrasekar ◽  
S. Laksmanan ◽  
Ju H. Park
Keyword(s):  
Neural Networks ◽  
State Estimation ◽  
Recurrent Neural Networks ◽  
Time Varying

Extended Kalman Filter–Based Pruning Method for Recurrent Neural Networks

1998 ◽  
Vol 10 (6) ◽  
pp. 1481-1505 ◽  
Author(s):  
John Sum ◽  
Lai-wan Chan ◽  
Chi-sing Leung ◽  
Gilbert H. Young
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Recurrent Neural Networks ◽  
Posterior Probability ◽  
Linear Time ◽  
Learning Methods ◽  
Pruning Method ◽  
Gradient Based

Pruning is one of the effective techniques for improving the generalization error of neural networks. Existing pruning techniques are derived mainly from the viewpoint of energy minimization, which is commonly used in gradient-based learning methods. In recurrent networks, extended Kalman filter (EKF)–based training has been shown to be superior to gradient-based learning methods in terms of speed. This article explains a pruning procedure for recurrent neural networks using EKF training. The sensitivity of a posterior probability is used as a measure of the importance of a weight instead of error sensitivity since posterior probability density is readily obtained from this training method. The pruning procedure is tested using three problems: (1) the prediction of a simple linear time series, (2) the identification of a nonlinear system, and (3) the prediction of an exchange-rate time series. Simulation results demonstrate that the proposed pruning method is able to reduce the number of parameters and improve the generalization ability of a recurrent network.

Sign in / Sign up

Export Citation Format

Share Document