Accuracy Estimates for Surrogate Solutions of Integral Equations by Neural Networks

0374354 - ÚI 2012 RIV CZ eng C - Konferenční příspěvek (zahraniční konf.)
Kůrková, Věra
Accuracy Estimates for Surrogate Solutions of Integral Equations by Neural Networks.
SOFSEM 2012: Theory and Practice of Computer Science. Vol. 2. Prague: Institute of Computer Science AS CR, 2012 - (Bieliková, M.; Friedrich, G.; Gottlob, G.; Katzenbeisser, S.; Špánek, R.; Turán, G.), s. 95-102. ISBN 978-80-87136-13-3.
[SOFSEM 2012. Conference on Current Trends in Theory and Practice of Computer Science /38./. Špindlerův Mlýn (CZ), 21.01.2012-27.01.2012]
Grant CEP: GA MŠMT OC10047
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: surrogate solutions by neural networks * Fredholm integral equations * network complexity
Kód oboru RIV: IN - Informatika

Surrogate solutions of integral equations by neural networks are investigated theoretically. Upper bounds on speed of convergence of approximate solutions computable by neural networks with increasing model complexity to exact solutions described by Fredholm theorem are derived.
Trvalý link: http://hdl.handle.net/11104/0207300