Graphical Jump Method for Neural Networks

Journal of Data Science

article

Jing Chang¹  Herbert K. H. Lee² 

[1] Hunan University of Art and Science;University of California

关键词: Jump Plot;    Model Selection;    Neural Network;   

DOI  :  10.6339/JDS.201710_15(4).00006

学科分类：土木及结构工程学

来源: JDS

【 摘 要 】

A graphical tool for choosing the number of nodes for a neural network is introduced. The idea is to fit the neural network with a range of numbers of nodes at first, and then generate a jump plot using a transformation of the mean square errors of the resulting residuals. A theorem is proven to show that the jump plot will select several candidate numbers of nodes among which one is the true number of nodes. Then a single node only test, which has been theoretically justified, is used to rule out erroneous candidates. The method has a sound theoretical background, yields good results on simulated datasets, and shows wide applicability to datasets from real research.

【 授权许可】

CC BY