Nonlinear stretching for enhanced learning of the backpropagation algorithm in target recognition

In spite of its relatively slow learning speed, backpropagation (BP) is one of the most popular neural network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the activation function in a BP algorithm to speed up the convergence in training. A target reco...

Full description

Saved in:
Bibliographic Details
Published in:Microwave and optical technology letters 1997-12, Vol.16 (6), p.334-337
Main Authors: Ge, Yi, Cha, Soyoung S., Zhang, Jiajun, Zhang, Li, He, Anzhi
Format: Article
Language:English
Subjects:
BP algorithm
moment invariants
nonlinear stretching
target recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In spite of its relatively slow learning speed, backpropagation (BP) is one of the most popular neural network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the activation function in a BP algorithm to speed up the convergence in training. A target recognition system that incorporates the approach and moment invariants is formulated and tested. The test results indicate that the speed of convergence can be effectively increased through appropriate selection of a stretch factor. © 1997 John Wiley & Sons, Inc. Microwave Opt Technol Lett 16: 334–337, 1997.
ISSN:0895-2477
1098-2760
DOI:10.1002/(SICI)1098-2760(19971220)16:6<334::AID-MOP4>3.0.CO;2-L