A DYNAMIC LEARNING NEURAL-NETWORK FOR REMOTE-SENSING APPLICATIONS

NCUIR > Research Center > Center for Space and Remote Sensing Research > journal & Dissertation > Item 987654321/27696

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/27696

Title:	A DYNAMIC LEARNING NEURAL-NETWORK FOR REMOTE-SENSING APPLICATIONS
Authors:	TZENG,YC;CHEN,KS;KAO,WL;FUNG,AK
Contributors:	太空及遙測研究中心
Keywords:	CLASSIFICATION
Date:	1994
Issue Date:	2010-06-29 18:52:27 (UTC+8)
Publisher:	中央大學
Abstract:	The neural network learning process is to adjust the network weighs to adapt the selected training data. Based on the polynomial basis function (PBF) modeled neural network that is a modified multilayer perceptrons (MLP) network, a dynamic learning algorithm (DL) is proposed in this paper. The presented learning algorithm makes use of Kalman filtering technique to update the network weights, in the sense that the stochastic characteristics of incoming data sets are implicitly incorporated into the network. The Kalman gains which represent the learning rates of the network weights updating are calculated by using the U-D factorization. By concatenating all of the network weights at each layer to form a long vector such that it can be updated without propagating back, the proposed algorithm improves the performance of convergence to which the back-propagation (BP) learning algorithm often suffers. Numerical illustrations are carried out using two categories of problems: multispectral imagery classification and surface parameters inversion. Results indicates the use of Kalman filtering algorithm not only substantially increases the convergence rate in the learning stage, but also enhances the separability for highly nonlinear boundaries problems, as compared to BP algorithm, suggesting that the proposed DL neural network provides a practical and potential tool for remote sensing applications.
Relation:	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Appears in Collections:	[Center for Space and Remote Sensing Research ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	777	View/Open

社群 sharing

Loading...