Přejít k obsahu


A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks

Citace: [] ZELINKA, J., ROMPORTL, J., MÜLLER, L. A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks. Lecture Notes in Artificial Intelligence, 2010, roč. 2010, č. 6231, s. 472-479. ISSN: 0302-9743
Druh: ČLÁNEK
Jazyk publikace: eng
Anglický název: A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks
Rok vydání: 2010
Místo konání: Heidelberg
Název zdroje: Springer
Autoři: Ing. Jan Zelinka , Ing. Jan Romportl Ph.D. , Doc. Ing. Luděk Müller Ph.D.
Abstrakt CZ: Tento článek popisuje apriorní a aposteriorní Machine Learning a ANN
Abstrakt EN: 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.
Klíčová slova

Zpět

Patička