Advantages of Artificial Neural Network in Neutron Spectra Unfolding

Advantages of using the artificial neural network method in neutron spectra unfolding are investigated in comparison with the maximum entropy unfolding method. By introducing the information entropy theory, we find that for the spectrum with the information entropy over 3.5, the four-layer feed-forw...

Full description

Saved in:
Bibliographic Details
Published inChinese physics letters Vol. 31; no. 7; pp. 69 - 72
Main Author 祝庆军 田立朝 杨晓虎 甘龙飞 赵娜 马燕云
Format Journal Article
LanguageEnglish
Published 01.07.2014
Subjects
Entropy
Entropy (Information)
Maximum entropy
Maximum entropy method
Mean square values
Neural networks
Neutron spectra
Spectra
中子谱
人工神经网络方法
人工神经网络模型
优势
信息熵理论
前馈神经网络
均方误差
最大熵法
Online AccessGet full text
ISSN0256-307X
1741-3540
DOI10.1088/0256-307X/31/7/072901

Cover

More Information
Summary:Advantages of using the artificial neural network method in neutron spectra unfolding are investigated in comparison with the maximum entropy unfolding method. By introducing the information entropy theory, we find that for the spectrum with the information entropy over 3.5, the four-layer feed-forward neural network （11-35-55-60） and the maximum entropy method generally demonstrate the same unfolding performance, while the spectrum with the information entropy lower than 3.5, the artificial neural network unfolding model is recommend due to the fact that the artificial neural network method has a stronger negative correlation between the entropy of the spectra and the mean squares error of the spectra than the maximum entropy method.
Bibliography:ZHU Qing-Jun, TIAN Li-Chao, YANG Xiao-Hu, GAN Long-Fei, ZHAO Na, MA Yan-Yun（ College of Science, National University of Defense Technology, Changsha 410073）
11-1959/O4
Advantages of using the artificial neural network method in neutron spectra unfolding are investigated in comparison with the maximum entropy unfolding method. By introducing the information entropy theory, we find that for the spectrum with the information entropy over 3.5, the four-layer feed-forward neural network （11-35-55-60） and the maximum entropy method generally demonstrate the same unfolding performance, while the spectrum with the information entropy lower than 3.5, the artificial neural network unfolding model is recommend due to the fact that the artificial neural network method has a stronger negative correlation between the entropy of the spectra and the mean squares error of the spectra than the maximum entropy method.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0256-307X
1741-3540
DOI:10.1088/0256-307X/31/7/072901