Přístupnostní navigace
E-application
Search Search Close
Publication detail
ŠKORPIL, V. ŠŤASTNÝ, J.
Original Title
Neural Networks Algorithms Analysis in Image Processing Application
Type
journal article - other
Language
English
Original Abstract
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.
Keywords
Radial Basis Function (RBF), Multi Layer Perceptron (MLP), Neural Network, Least Mean Square (LMS)
Authors
ŠKORPIL, V.; ŠŤASTNÝ, J.
RIV year
2008
Released
30. 11. 2008
Publisher
GESTS
Location
Korea
ISBN
1738-9682
Periodical
International Transactions on Communication and Signal Processing
Year of study
12
Number
11
State
Republic of Korea
Pages from
258
Pages to
267
Pages count
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" }