Original title:
Accuracy Estimates for Surrogate Solutions of Integral Equations by Neural Networks
Authors:
Kůrková, Věra Document type: Papers Conference/Event: SOFSEM 2012. Conference on Current Trends in Theory and Practice of Computer Science /38./, Špindlerův Mlýn (CZ), 2012-01-21 / 2012-01-27
Year:
2012
Language:
eng Abstract:
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.
Keywords:
Fredholm integral equations; network complexity; surrogate solutions by neural networks Project no.: CEZ:AV0Z10300504 (CEP), OC10047 (CEP) Funding provider: GA MŠk Host item entry: SOFSEM 2012: Theory and Practice of Computer Science, ISBN 978-80-87136-13-3
Institution: Institute of Computer Science AS ČR
(web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences. Original record: http://hdl.handle.net/11104/0207300