Synthesis of a Neural Network via Analytic Programming Methodology
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F13%3A43869450" target="_blank" >RIV/70883521:28140/13:43869450 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Synthesis of a Neural Network via Analytic Programming Methodology
Original language description
This paper introduces innovative method of an artificial neural network (ANN) optimization (synthesis) by means of Analytic Programming (AP). The method proves itself to be especially effective when formally identified non-neural parts of the heating plant model need to be made more accurate. Asynchronous distribu-tion plays the key role here as the heating plant behavior data has to be acquired from a very large database and therefore learning of ANN may require a lot of computation time. The method was successfully tested on the real life problems as well as on widely recognized benchmark functions with respect to the function approximation, prediction and problems. The ANN synthesis software was de-signed based on .NET Framework technology. The resulting software is capable of automatic synthesis and optimizing the ANN based on the user-given data within a reasonable time. The ANN synthesis proves to be a useful and efficient tool for nonlinear modeling in comparison with competing
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/ED2.1.00%2F03.0089" target="_blank" >ED2.1.00/03.0089: The Centre of Security, Information and Advanced Technologies (CEBIA-Tech)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Nostradamus: Modern Methods of Prediction, Modeling and Analysis of Nonlinear Systems
ISBN
978-3-642-33226-5
ISSN
2194-5357
e-ISSN
—
Number of pages
16
Pages from-to
225-240
Publisher name
Springer-Verlag Berlin
Place of publication
Heidelberg
Event location
Ostrava
Event date
Sep 5, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—