Self-learning Genetic Algorithm for Neural Network Topology Optimization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F47813059%3A19520%2F15%3A%230003693" target="_blank" >RIV/47813059:19520/15:#0003693 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-319-19728-9_15" target="_blank" >http://dx.doi.org/10.1007/978-3-319-19728-9_15</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-19728-9_15" target="_blank" >10.1007/978-3-319-19728-9_15</a>
Alternative languages
Result language
čeština
Original language name
Self-learning Genetic Algorithm for Neural Network Topology Optimization
Original language description
The aim of this paper is presentation of encoding for self-adaptation of genetic algorithms which is suitable for neural network topology optimization. Comparing to previous approaches there is designed the encoding for self-adaptation not only one parameter or several ones but for all possible parameters of genetic algorithms at the same time. The proposed self-learning genetic algorithm is compared with a standard genetic algorithm. The main advantage of this approach is that it makes possible to solve wide range of optimization problems without setting parameters for each type of problem in advance.
Czech name
Self-learning Genetic Algorithm for Neural Network Topology Optimization
Czech description
The aim of this paper is presentation of encoding for self-adaptation of genetic algorithms which is suitable for neural network topology optimization. Comparing to previous approaches there is designed the encoding for self-adaptation not only one parameter or several ones but for all possible parameters of genetic algorithms at the same time. The proposed self-learning genetic algorithm is compared with a standard genetic algorithm. The main advantage of this approach is that it makes possible to solve wide range of optimization problems without setting parameters for each type of problem in advance.
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Smart Innovation Systems and Technologies. Agent and Multi-Agent Systems: Technologies and Applications
ISBN
978-3-319-19728-9
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
179-188
Publisher name
Springer International Publishing
Place of publication
Heidelberg
Event location
Sorrento
Event date
Jun 17, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000359295700015