Rates of convergence of the recursive radial basis function networks

J. Mazurek, A. Krzyzak, A. Cichocki

Research output: Contribution to journalConference articlepeer-review

4 Citations (Scopus)

Abstract

Recursive radial basis function (RRBF) neural networks are introduced and discussed. We study in detail the nets with diagonal receptive field matrices. Parameters of the networks are learned by a simple procedure. Convergence and the rates of convergence of RRBF nets in the mean integrated absolute error (MIAE) sense are studied under mild conditions imposed on some of the network parameters. Obtained results give also upper bounds on the performance of RRBF nets learned by minimizing empirical L1 error.

Original languageEnglish
Pages (from-to)3317-3320
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
Publication statusPublished - 1997
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger
Duration: 21 Apr 199724 Apr 1997

Fingerprint

Dive into the research topics of 'Rates of convergence of the recursive radial basis function networks'. Together they form a unique fingerprint.

Cite this