Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
ŠKORPIL, V. ŠŤASTNÝ, J.
Originální název
Neural Networks Algorithms Analysis in Image Processing Application
Typ
článek v časopise - ostatní, Jost
Jazyk
angličtina
Originální abstrakt
The paper describes the algorithms for construction and learning of the Radial Basis Function (RBF) and the MLP (Multi Layer Perceptron) neural networks. We compared results obtained by a using of learning algorithms LMS (Least Mean Square) and gradient algorithms and results obtained by a using of algorithms APC-III and K-means for hidden layer contruction of RBF neural network and algorithm Back-Propagation (BP) of MLP neural network. The real technological scene for object identification by means of MLP and RBF neural networks was simulated with digitization of two-dimensional objects.
Klíčová slova
Radial Basis Function (RBF), Multi Layer Perceptron (MLP), Neural Network, Least Mean Square (LMS)
Autoři
ŠKORPIL, V.; ŠŤASTNÝ, J.
Rok RIV
2008
Vydáno
30. 11. 2008
Nakladatel
GESTS
Místo
Korea
ISSN
1738-9682
Periodikum
International Transactions on Communication and Signal Processing
Ročník
12
Číslo
11
Stát
Korejská republika
Strany od
258
Strany do
267
Strany počet
10
BibTex
@article{BUT48416, author="Vladislav {Škorpil} and Jiří {Šťastný}", title="Neural Networks Algorithms Analysis in Image Processing Application", journal="International Transactions on Communication and Signal Processing", year="2008", volume="12", number="11", pages="258--267", issn="1738-9682" }