Determination of the number of hidden units from a statistical viewpoint

Author

Ayasaka, Taichi ; Agiwara, Katsuyukhi ; Toda, Naohiro ; Usui, Shiro

Author_Institution

Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan

Volume

1

fYear

1999

fDate

1999

Firstpage

240

Abstract

One of the important problems for 3-layered neural networks (3-LNN) is to determine the optimal network structure with high generalization ability. Although this can be formulated in terms of a statistical model selection, there remains a problem in applying traditional criteria for 3-LNN. We suggest the type of effective criteria for the model selection problem of 3-LNN by analyzing the statistical properties of some simplified nonlinear models. Results of numerical experiments are also presented

Keywords

generalisation (artificial intelligence); multilayer perceptrons; statistical analysis; generalization; hidden unit determination; nonlinear models; numerical experiments; optimal network structure; regression; statistical model selection; statistical properties; three-layered neural networks; Artificial neural networks; Computer networks; Error analysis; Gaussian distribution; Information science; Neural networks; Nominations and elections; Parameter estimation; Physics computing; Polynomials;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-5871-6

Type

conf

DOI

10.1109/ICONIP.1999.843993

Filename

843993