Classification and Prediction with Neural Networks

View Sample PDF

Author(s): Arnošt Veselý (Czech University of Life Sciences, Czech Republic)
Copyright: 2009
Pages: 32
Source title: Data Mining and Medical Knowledge Management: Cases and Applications
Source Author(s)/Editor(s): Petr Berka (University of Economics, Prague, Czech Republic), Jan Rauch (University of Economics, Prague, Czech Republic)and Djamel Abdelkader Zighed (University of Lumiere Lyon 2, France)
DOI: 10.4018/978-1-60566-218-3.ch004

Keywords: Data Mining / Data Mining and Databases / Information Science Reference / Library & Information Science

Purchase

View Classification and Prediction with Neural Networks on the publisher's website for pricing and purchasing information.

Abstract

This chapter deals with applications of artificial neural networks in classification and regression problems. Based on theoretical analysis it demonstrates that in classification problems one should use cross-entropy error function rather than the usual sum-of-square error function. Using gradient descent method for finding the minimum of the cross entropy error function, leads to the well-known backpropagation of error scheme of gradient calculation if at the output layer of the neural network the neurons with logistic or softmax output functions are used. The author believes that understanding the underlying theory presented in this chapter will help researchers in medical informatics to choose more suitable network architectures for medical applications and that it helps them to carry out the network training more effectively.

The IRMA Community

Research IRM

Classification and Prediction with Neural Networks

Purchase

Abstract

Related Content

IRMA Sponsors