INFORMATICA

Informatica

0868-49520868-4952

INF3301

10.3233/INF-1992-3301

Research article

On training sample size and complexity of artificial neural net classifier

Jain

Anil

Raudys

Šarūnas

Department of Computer Science, Michigan State University, East Lansing, MI 48824, USADepartment of Data Analysis, Institute of Mathematics and Informatics, 2600 Vilnius, Akademijos St.4, Lithuania

01011992

33301337

Small training sample effects common in statistical classification and artificial neural network classifier design are discussed. A review of known small sample results are presented, and peaking phenomena related to the increase in the number of features and the number of neurons is discussed.

Keywordsfeed forward neural netsclassification error training samplesdimensionalitycomplexitypeaning phenomenon