The performance of approximating ordinary differential equations by neural nets

The dynamics of many systems are described by ordinary differential equations (ODE). Solving ODEs with standard methods (i.e. numerical integration) needs a high amount of computing time but only a small amount of storag
The dynamics of many systems are described by ordinary differential equations (ODE). Solving ODEs with standard methods (i.e. numerical integration) needs a high amount of computing time but only a small amount of storage memory. For some applications, e.g. short time weather forecast or real time robot control, long computation times are prohibitive. Is there a method which uses less computing time (but has drawbacks in other aspects, e.g. memory), so that the computation of ODEs gets faster? We will try to discuss this question for the assumption that the alternative computation method is a neural network which was trained on ODE dynamics and compare both methods using the same approximation error. This comparison is done with two different errors. First, we use the standard error that measures the difference between the approximation and the solution of the ODE which is hard to characterize. But in many cases, as for physics engines used in computer games, the shape of the approximation curve is important and not the exact values of the approximation. Therefore, we introduce a subjective error based on the Total Least Square Error (TLSE) which gives more consistent results. For the final performance comparison, we calculate the optimal resource usage for the neural network and evaluate it depending on the resolution of the interpolation points and the inter-point distance. Our conclusion gives a method to evaluate where neural nets are advantageous over numerical ODE integration and where this is not the case. Index Terms—ODE, neural nets, Euler method, approximation complexity, storage optimization.
show moreshow less

Download full text files

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

    Share in Twitter Search Google Scholar
Metadaten
Author:Josef Fojdl, Rüdiger W. Brause
URN:urn:nbn:de:hebis:30-79308
Document Type:Preprint
Language:English
Date of Publication (online):2010/09/09
Year of first Publication:2008
Publishing Institution:Univ.-Bibliothek Frankfurt am Main
Release Date:2010/09/09
Tag:Euler method ; ODE ; approximation complexity ; neural nets ; storage optimization
Source:in: IEEE 20th Int. Conf on Tools with Art. Intell., ICTAI-2008, Dayton, 2008, IEEE Press, 2008, (preprint version)
HeBIS PPN:228108934
Institutes:Informatik
Dewey Decimal Classification:004 Datenverarbeitung; Informatik
Sammlungen:Universitätspublikationen
Licence (German):License Logo Veröffentlichungsvertrag für Publikationen

$Rev: 11761 $