Treffer: A minimax method for learning functional networks

Title:
A minimax method for learning functional networks
Source:
Neural processing letters. 11(1):39-49
Publisher Information:
Dordrecht: Springer, 2000.
Publication Year:
2000
Physical Description:
print, 12 ref
Original Material:
INIST-CNRS
Document Type:
Fachzeitschrift Article
File Description:
text
Language:
English
Author Affiliations:
Department of Applied Mathematics and Computational Sciences, University of Cantabria, Spain
Ocean and Coastal Research Group, University of Cantabria, Spain
ISSN:
1370-4621
Rights:
Copyright 2000 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Electronics
Accession Number:
edscal.1265831
Database:
PASCAL Archive

Weitere Informationen

In this paper, a minimax method for learning functional networks is presented. The idea of the method is to minimize the maximum absolute error between predicted and observed values. In addition, the invertible functions appearing in the model are assumed to be linear convex combinations of invertible functions. This guarantees the invertibility of the resulting approximations. The learning method leads to a linear programming problem and then: (a) the solution is obtained in a finite number of iterations, and (b) the global optimum is attained. The method is illustrated with several examples of applications, including the Hénon and Lozi series. The results show that the method outperforms standard least squares direct methods.