Training strategies for Radial Basis Function Neural Networks: A study applied to prostate cancer prognosis

Author

Rautenberg, Stephan ; de Re, A.M. ; Hernandes, F. ; Urio, Paulo Roberto ; Padilha, V. Alexandre ; Jose de Paula Castanho, M.

Author_Institution

Dept. de Cienc. da Comput., Univ. Estadual do Centro-Oeste, Guarapuava, Brazil

fYear

2012

fDate

1-5 Oct. 2012

Firstpage

1

Lastpage

5

Abstract

A development of a Radial Basis Function Neural Network applied to the prostate cancer prognosis is presented. Five training strategies were implemented: the Successive Approximation algorithm; the k-means algorithm; Ainet; Ainet + k-means, and Successive Approximation + k-means. Comparing all tested strategies, the Successive Approximation training strategy obtained the best fitness measure. And comparing this result to other previously studies, we concluded that the use of Radial Basis Function Neural Networks becomes a viable alternative to the prostate cancer prognosis.

Keywords

approximation theory; cancer; medical computing; radial basis function networks; Ainet + k-means; k-means algorithm; prostate cancer prognosis; radial basis function neural networks; successive approximation + k-means; successive approximation algorithm; training strategies; Artificial neural networks; CD-ROMs; Prostate cancer; Radial basis function networks; Training; Tumors; Neural Networks Training Strategies; Prostate Cancer; Radial Basis Function Neural Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Informatica (CLEI), 2012 XXXVIII Conferencia Latinoamericana En

Conference_Location

Medellin

Print_ISBN

978-1-4673-0794-9

Type

conf

DOI

10.1109/CLEI.2012.6427175

Filename

6427175