A novel approach of the approximation by patterns using hybrid RBF NN with flexible parameters
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952470" target="_blank" >RIV/49777513:23520/18:43952470 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-030-00211-4_21" target="_blank" >http://dx.doi.org/10.1007/978-3-030-00211-4_21</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-00211-4_21" target="_blank" >10.1007/978-3-030-00211-4_21</a>
Alternative languages
Result language
angličtina
Original language name
A novel approach of the approximation by patterns using hybrid RBF NN with flexible parameters
Original language description
This paper describes a new solution to the optimization task of approximation by radial-basis-function (RBF) neural network. The proposed method is addressed to the problem of variable shape parameters for data using the RBF. It involves the max-min algorithm, the RBF neural network, the algorithm for placing new neuron’s centers and the structure of the future deep learning complex neural network (NN).
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA17-05534S" target="_blank" >GA17-05534S: Meshless methods for large scattered spatio-temporal vector data visualization</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computational and Statistical Methods in Intelligent Systems
ISBN
978-3-030-00210-7
ISSN
2194-5357
e-ISSN
2194-5365
Number of pages
11
Pages from-to
225-235
Publisher name
Springer
Place of publication
Cham
Event location
Szczecin
Event date
Sep 12, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—