Title: A priori and a posteriori machine learning and nonlinear artificial neural networks
Other Titles: Apriorní a aposteriorní Machine Learning a ANN
Authors: Zelinka, Jan
Romportl, Jan
Müller, Luděk
Citation: ZELINKA, Jan; ROMPORTL, Jan; MÜLLER, Luděk. A priori and a posteriori machine learning and nonlinear artificial neural networks. In: Progress in pattern recognition, image analysis, computer vision, and applications. Berlin: Springer, 2010, p. 472-479. (Lectures notes in computer science; 6231). ISBN 978-3-642-15759-2.
Issue Date: 2010
Publisher: Springer
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/JanZelinka_2010_APrioriandA
ISBN: 978-3-642-15759-2
Keywords: umělá neuronová síť;strojové učení
Keywords in different language: artificial neural network;machine learning
Abstract in different language: The main idea of a priori machine learning is to apply a machine learning method on a machine learning problem itself.We call it "a priori" because the processed data set does not originate from any measurement or other observation.Machine learning which deals with any observation is called "posterior". The paper describes how posterior machine learning can be modified by a priori machine learning. A priori and posterior machine learning algorithms are proposed for artificial neural network training and are tested in the task of audio-visual phoneme classification.
Rights: © Jan Zelinka - Jan Romportl - Luděk Müller
Appears in Collections:Články / Articles (MMI)
Články / Articles (KKY)

Files in This Item:
File Description SizeFormat 
JanZelinka_2010_APrioriandA.pdfPlný text166,56 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/17159

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.