USE OF NEW METHOD FOR LEARNING OF NEURAL NETWORKS
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F63468352%3A_____%2F04%3A%230000081" target="_blank" >RIV/63468352:_____/04:#0000081 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
USE OF NEW METHOD FOR LEARNING OF NEURAL NETWORKS
Original language description
Neural networks are used for classification and prediction of data at future. For training of neural networks we can use the backpropagation procedure, although there are the limitations associated with this technique and these problems are well documented. In this paper a training procedure is described, that can achieve the needed accuracy at limited training time. We then use the data from simulation of time series and we compare the proposed methods with the backpropagation method in our simulator.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
N - Vyzkumna aktivita podporovana z neverejnych zdroju
Others
Publication year
2004
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 International Conference on Soft Computing Applied in Computer and Economic Environments
ISBN
80-7314-025-X
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
Evropský polytechnický institut, s.r.o.
Place of publication
Kunovice
Event location
Kunovice
Event date
Jan 1, 2004
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—