DocumentCode
3197237
Title
Overcoming recurrent neural networks´ compactness limitation for neurofiltering
Author
Lo, James Ting-Ho ; Yu, Lei
Author_Institution
Dept. of Math. & Stat., Maryland Univ., Baltimore, MD, USA
Volume
4
fYear
1997
fDate
9-12 Jun 1997
Firstpage
2181
Abstract
Two range extenders and one range reducer for neural filtering are disclosed. The two range extenders are essentially an EKF and an accumulator respectively, which are used to extend the range of a recurrent neural network to cover the range of a signal process to be estimated. The range reducer disclosed is a differencer, which is used to reduce the range of the measurement process available for filtering
Keywords
Kalman filters; covariance matrices; filtering theory; nonlinear filters; recurrent neural nets; signal processing; accumulator; compactness limitation; differencer; extended Kalman filter; neurofiltering; range extenders; range reducer; recurrent neural networks; Aircraft navigation; Extraterrestrial measurements; Filtering; Neural networks; Recurrent neural networks; Satellite navigation systems; Signal processing; Size measurement; Target tracking; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.614246
Filename
614246
Link To Document