Minimum complexity PDF estimation for correlated data

Author

Sardo, Lucia ; Kittler, Josef

Author_Institution

Dept. of Electron. & Electr. Eng., Surrey Univ., Guildford, UK

Volume

2

fYear

1996

fDate

25-29 Aug 1996

Firstpage

750

Abstract

We investigate the previously overlooked issue in pdf (probability density function) estimation using radial basis functions (RBF), namely the effect of data correlation on the complexity of the RBF network architecture. We propose two simple scalar measures of data correlation. We then introduce a maximum penalized likelihood (MPL) function as a performance criterion for training such pdf estimators where the penalty term is defined in terms of these scalar measures. The proposed MPL criterion favours minimum complexity estimators. The advocated methodology is validated experimentally

Keywords

correlation theory; feedforward neural nets; identification; probability; MPL criterion; RBF network architecture; correlated data; data correlation; maximum penalized likelihood function; minimum complexity PDF estimation; performance criterion; probability density function; radial basis functions; Algorithm design and analysis; Artificial neural networks; Kernel; Least squares approximation; Neural networks; Probability density function; Radial basis function networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.546923

Filename

546923