Pre-processing for the RBF-NNs with flexible parameters for multi-dimensional data
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43958035" target="_blank" >RIV/49777513:23520/18:43958035 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/CINTI.2018.8928225" target="_blank" >http://dx.doi.org/10.1109/CINTI.2018.8928225</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CINTI.2018.8928225" target="_blank" >10.1109/CINTI.2018.8928225</a>
Alternative languages
Result language
angličtina
Original language name
Pre-processing for the RBF-NNs with flexible parameters for multi-dimensional data
Original language description
This paper describes a solution to the optimization task of approximation by radial-basis-function (RBF) neural network. The proposed method is created for the teacher NNs for complex system and is addressed to the problem of variable shape parameters for data using the RBF. It involves the k-means algorithm, the RBF neural network, the ideas of the algorithm for placing new centers of neurons and the structure of the future deep learning complex neural network.
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
18th IEEE International Symposium on Computational Intelligence and Informatics
ISBN
978-1-72811-117-9
ISSN
2471-9269
e-ISSN
—
Number of pages
6
Pages from-to
19-24
Publisher name
IEEE
Place of publication
Danvers
Event location
Budapest
Event date
Nov 21, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—