True risk bounds for the regression of real-valued functions

Author

Kil, Rhee Man ; Koo, Imhoi

Author_Institution

Div. of Appl. Math., Korea Adv. Inst. of Sci. & Technol., Taejeon, South Korea

Volume

1

fYear

2003

fDate

20-24 July 2003

Firstpage

507

Abstract

This paper presents a new form of true risk bounds for the regression of real-valued functions. The goal of machine learning is minimizing the true risk (or general error) for the whole distribution of sample space, not just a set of training samples. However, the true risk cannot be estimated accurately with the finite number of samples. In this sense, we derive the form of true risk bounds which may provide the useful guideline for the optimization of learning models. Through the simulation for the function approximation, we have shown that the prediction of true risk bounds based on the suggested functional norm is well fitted to the empirical data.

Keywords

function approximation; learning (artificial intelligence); optimisation; regression analysis; risk analysis; empirical data; error approximation; function approximation; general error; learning models; machine learning; optimization; performance prediction method; real-valued functions; regression error; true risk bounds; Convergence; Function approximation; Guidelines; Kernel; Machine learning; Mathematics; Paper technology; Predictive models; Recruitment; Virtual colonoscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223398

Filename

1223398