Creator:

Gołąbek, Piotr ; Kosiński, Witold

Contributor:

Rutkowska, Danuta - ed. ; Zadeh, Lotfi A. - ed.

Title:

Adaptation of regularization parameters in NM-Delta networks

Subtitle:

Neuro-Fuzzy and Soft Computing

Group publication title:

AMCS, volume 10 (2000)

Subject and Keywords:

NM-Delta ; M-Delta ; regularization ; Levenberg-Marquardt ; quasi-Newton

Abstract:

The paper describes an application of regularization techniques to an automatic choice of parameters driving the learning process in the NM-Delta neural network architecture. The heterogeneous learning algorithm is identified as very similar to the Levenberg-Marquardt method but with a considerably smaller computational cost and different justification of parameter selection. The performance of the modified algorithm proves to be comparable with that of the Levenberg-Marquardt.

Publisher:

Zielona Góra: Uniwersytet Zielonogórski

Date:

2000

Resource Type:

artykuł

Pages:

779-790

Source:

AMCS, volume 10, number 4 (2000) ; click here to follow the link

Language:

eng

Rights:

Biblioteka Uniwersytetu Zielonogórskiego