ZIB

Treffer pro Seite

Treffer 1 - 1 | 1 Treffer

Sortierung

Digitale Medien

Training neural networks with noisy data as an ill-posed problem (2000)

Burger, Martin ; Engl, Heinz W.

Springer

Advances in computational mathematics 13 (2000), S. 335-354

zur Merkliste hinzufügen auf der Merkliste

Details

ISSN: 1572-9044

Schlagwort(e): ill-posed problems ; least-squares collocation ; neural networks ; network training ; regularization

Quelle: Springer Online Journal Archives 1860-2000

Thema: Mathematik

Notizen: Abstract This paper is devoted to the analysis of network approximation in the framework of approximation and regularization theory. It is shown that training neural networks and similar network approximation techniques are equivalent to least-squares collocation for a corresponding integral equation with mollified data. Results about convergence and convergence rates for exact data are derived based upon well-known convergence results about least-squares collocation. Finally, the stability properties with respect to errors in the data are examined and stability bounds are obtained, which yield rules for the choice of the number of network elements.

Materialart: Digitale Medien

URL: http://dx.doi.org/10.1023/A:1016641629556

Permalink

Bibliothek	Standort	Signatur	Band/Heft/Jahr	Verfügbarkeit

Andere fanden auch interessant ...

Artikel (Nationallizenzen)

Volltext

Treffer 1 - 1 | 1 Treffer