A New Parameter Selection Method of Neural Network

A new parameter selection method of neural network is presented after researching parameter selection method of neural network deeply, and it is applied to surface defect online inspection system of cold rolled strips. The method exerted the merits of small-samples fully which was utilized to train...

Full description

Saved in:
Bibliographic Details
Published in2008 International Conference on Multimedia and Ubiquitous Engineering (mue 2008) pp. 378 - 383
Main Authors Gui-fang Wu, Se-young Jang, Hoon-sung Kwak, Jie-xin Pu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2008
Subjects
Automation
Cold rolled strip
Computer networks
Educational institutions
Inspection
Multimedia systems
Neural network
Neural networks
Parameter selection
Pervasive computing
Real time systems
Small sample
Strips
Testing
Online AccessGet full text

Cover

More Information
Summary:A new parameter selection method of neural network is presented after researching parameter selection method of neural network deeply, and it is applied to surface defect online inspection system of cold rolled strips. The method exerted the merits of small-samples fully which was utilized to train and test neural network by every possible combination of parameters to get a group of neural network parameters by plotting histogram of recognition rate under different parameter combinations, and the parameters are regarded as optimized parameters of neural network. Experiments showed that a best recognition effect by using the parameters for neural network which are selected by the new parameter selection method can be achieved among all the parameters selected randomly for surface defect of cold rolled strips.
ISBN:9780769531342
0769531342
DOI:10.1109/MUE.2008.99