Osaka Prefecture University Repository >
D.Former Osaka Prefecture University:(1955-2004) >
0200.College of Agriculture/Graduate School of Agriculture and Biological Sciences >
Bulletin of the University of Osaka Prefecture. Ser. B, Agriculture and biology >
Vol.43 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10466/3306

Title: Kalman Filter Neuron Training
Authors: MURASE, Haruhiko
KOYAMA, Shuhei
Issue Date: 31-Mar-1991
Publisher: University of Osaka Prefecture
Citation: Bulletin of the University of Osaka Prefecture. Ser. B, Agriculture and biology. 1991, 43, p.91-101
Abstract: An attempt of implementing Kalman filter algorithm in the procedure for training the neural network was made and evaluated. The Kalman filter neuron training program (KNT) was coded. The performance of Kalman filter in KNT was compared to commonly used neuron training algorithm. The study revealed that KNT requires much less calculation time to accomplish neuron training than commonly used other algorithms do. KNT also gave much smaller final error than any other algorithms tested in this study.
URI: http://hdl.handle.net/10466/3306
Appears in Collections:Vol.43

Files in This Item:

File Description SizeFormat
KJ00004361205.pdf423.81 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.