DocumentCode
2941563
Title
Application of function link net to recognition of radar targets
Author
Deshuang, Huang ; Erke, Mao ; Yueqiu, Han
Author_Institution
Inst. of Autom., Beijing Inst. of Technol., China
Volume
5
fYear
1995
fDate
9-12 May 1995
Firstpage
3487
Abstract
This paper studies the mechanism for classification of feedforward neural networks from the geometric viewpoints. It is pointed out that the multilayer perceptron networks (MLPNs) realize hyperplane divisions in the pattern space, and the FLN realize hypercurved divisions. We give a form of generalized function link nets (GFLN), and discuss the application of a special GFLN to recognition of radar targets, and give several experimental results
Keywords
feedforward neural nets; multilayer perceptrons; pattern classification; radar computing; radar target recognition; classification; experimental results; feedforward neural networks; generalized function link nets; hypercurved divisions; hyperplane divisions; multilayer perceptron networks; pattern space; radar targets recognition; Automation; Feedforward neural networks; Laboratories; Logic; Neural networks; Nonhomogeneous media; Pattern recognition; Radar applications; Target recognition; Transfer functions;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location
Detroit, MI
ISSN
1520-6149
Print_ISBN
0-7803-2431-5
Type
conf
DOI
10.1109/ICASSP.1995.479737
Filename
479737
Link To Document