OPTIMIZATION OF MODELS: LOOKING FOR THE BEST STRATEGY
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F07%3A03133126" target="_blank" >RIV/68407700:21230/07:03133126 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
OPTIMIZATION OF MODELS: LOOKING FOR THE BEST STRATEGY
Original language description
When parameters of model are being adjusted, model is learning to mimic the behaviour of a real world system. Optimization methods are responsible for parameters adjustment. The problem is that each real world system is different and its model should beof different complexity. It is almost impossible to decide which optimization method will perform the best (optimally adjust parameters of the model). In this paper we compare the performance of several methods for nonlinear parameters optimization. Thegradient based methods such as Quasi-Newton or Conjugate Gradient are compared to several nature inspired methods. We designed an evolutionary algorithm selecting the best optimization methods for models of various complexity. Our experiments proved thatthe evolution of optimization methods for particular problems is very promising approach.
Czech name
Optimalizace modelů: hledání nejlepší strategie
Czech description
V tomto článku porovnáváme výsledky mnoha metod (gradientních, genetika, hejna) pro optimalizaci spojitých parametrů modelu. Navrhli jsme evoluční algoritmus, který vhodné optimalizační metody vybere automaticky na základě charakteru dat. První výsledkynaznačují, že se jedná o velmi slibný přístup.
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/KJB201210701" target="_blank" >KJB201210701: Automated Knowledge Extraction</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2007
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 6th EUROSIM Congress on Modelling and Simulation
ISBN
978-3-901608-32-2
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
314-320
Publisher name
ARGESIM
Place of publication
Vienna
Event location
Ljubljana
Event date
Sep 9, 2007
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—