Adaptive Differential Evolution: Application to Nonlinear Regression
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F07%3AA0800LAQ" target="_blank" >RIV/61988987:17310/07:A0800LAQ - isvavai.cz</a>
Alternative codes found
RIV/61988987:17310/07:A1000LAQ
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Adaptive Differential Evolution: Application to Nonlinear Regression
Original language description
Adaptation of control parameters in differential evolution is considered. Five adaptive variants of differential evolution are applied to the estimation of parameters in nonlinear regression models and their performance is compared experimentally with the adaptive controlled random search algorithm tailored especially for these problems. The NIST nonlinear regression datasets are used as a benchmark. Two of five tested variants of adaptive differential evolution perform almost as reliable as the adaptive controlled random search algorithm and one of these two variants converges only slightly slower and its time requirements are almost comparable with the adaptive controlled random search.
Czech name
Adaptivní diferenciální dvoluce: Aplicace v nelineární regresi
Czech description
V článku jsou popsány různé přístupy k adaptaci řídicích parametrů v algoritmu diferenciální evoluce. Pět variant adaptivní diferenciální evoluce bylo experimentálně porovnáno v ulohách odhadu parametrů nelineárních regresních modelů na úlohách NIST se specializovaným CRS algorimem. Efektivnost dvou variant byla téměř srovnatelná s algoritmem CRS.
Classification
Type
D - Article in proceedings
CEP classification
BB - Applied statistics, operational research
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA201%2F05%2F0284" target="_blank" >GA201/05/0284: Evolutionary algorithms with competing and cooperating heuristics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>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 International Multiconference on Computer Science and Information Technology
ISBN
—
ISSN
1896-7094
e-ISSN
—
Number of pages
10
Pages from-to
193-202
Publisher name
PTI
Place of publication
Wisla
Event location
Wisla
Event date
Oct 15, 2007
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—