A new view on regularization theory

Author

Chen, Zhe ; Haykin, Simon

Author_Institution

Commun. Res. Lab., McMaster Univ., Hamilton, Ont., Canada

Volume

3

fYear

2001

fDate

2001

Firstpage

1642

Abstract

The paper provides a new viewpoint on regularization theory from different perspectives. It is shown that the regularized solution can be derived from the Fourier transformation operator in the transformation domain and with equivalent form from the linear differential operator in the spatial domain. The state-of-the-art research in regularization is briefly reviewed with extended discussions on Occam´s razor, minimum length description, Bayesian framework, pruning algorithms, statistical learning theory, and equivalent regularization

Keywords

Bayes methods; Fourier transforms; information theory; learning (artificial intelligence); neural nets; Bayesian framework; Fourier transformation operator; Occam razor; equivalent regularization; linear differential operator; minimum length description; pruning algorithms; regularization theory; regularized solution; spatial domain; statistical learning theory; transformation domain; Adaptive systems; Bayesian methods; Computer vision; Hilbert space; Image reconstruction; Image restoration; Inverse problems; Machine learning; Power engineering and energy; Statistical learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2001 IEEE International Conference on

Conference_Location

Tucson, AZ

ISSN

1062-922X

Print_ISBN

0-7803-7087-2

Type

conf

DOI

10.1109/ICSMC.2001.973520

Filename

973520