Martin Burger, Heinz Engl,
"Training neural networks with noisy data as an ill-posed problem"
, in Advances in Computational Mathematics, 2000, M. Burger and H.W. Engl, Training neural networks with noisy data as an ill-posed problem, Adv. Comp. Math. 13 (2000), 335-354.
Original Titel:
Training neural networks with noisy data as an ill-posed problem
Sprache des Titels:
Englisch
Englische Kurzfassung:
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.
Journal:
Advances in Computational Mathematics
Erscheinungsjahr:
2000
Notiz zum Zitat:
M. Burger and H.W. Engl, Training neural networks with noisy data as an ill-posed problem, Adv. Comp. Math. 13 (2000), 335-354.
Publikationstyp:
Aufsatz / Paper in sonstiger referierter Fachzeitschrift
Forschungs-