bibtype	C - Conference Paper (international conference)
ARLID	0085844
utime	20240103184432.3
mtime	20070925235959.9
title (primary) (eng)	Recurrent Bayesian Reasoning in Probabilistic Neural Networks
specification	page_count 10 s.
serial	ARLID cav_un_epca*0085843 ISBN 3-540-74693-5 title Artificial Neural Networks - ICANN 2007 part_num Part I. part_title SL 1 - Theoretical Computer Science and General Issues page_num 129-138 publisher place Berlin name Springer year 2007 editor name1 Marques de Sá name2 J. editor name1 Alexandre name2 L. A. editor name1 Duch name2 W. editor name1 Mandic name2 D.
title (cze)	Rekurentní bayesovské odvozování v pravděpodobnostních neuronových sítích
keyword	neural networks
keyword	probabilistic approach
keyword	distribution mixtures
author (primary)	ARLID cav_un_auth*0101091 name1 Grim name2 Jiří institution UTIA-B full_dept Department of Pattern Recognition fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author	ARLID cav_un_auth*0230019 name1 Hora name2 Jan institution UTIA-B fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
cas_special	project project_id 507752 country XE agency EC ARLID cav_un_auth*0200689 project project_id 1M0572 agency GA MŠk ARLID cav_un_auth*0001814 project project_id 2C06019 agency GA MŠk country CZ ARLID cav_un_auth*0216518 project project_id GA102/07/1594 agency GA ČR ARLID cav_un_auth*0228611 research CEZ:AV0Z10750506 abstract (eng) Considering the probabilistic approach to neural networks in the framework of statistical pattern recognition we assume approximation of class-conditional probability distributions by finite mixtures of product components. The mixture components can be interpreted as probabilistic neurons in neurophysiological terms and, in this respect, the fixed probabilistic description becomes conflicting with the well known short-term dynamic properties of biological neurons. We show that some parameters of PNN can be ``released'' for the sake of dynamic processes without destroying the statistically correct decision making. In particular, we can iteratively adapt the mixture component weights or modify the input pattern in order to facilitate the correct recognition. abstract (cze) Rekurentní bayesovské odvozování v pravděpodobnostních neuronových sítích action ARLID cav_un_auth*0230020 name International Conference on Artificial Neural Networks /17./ place Porto dates 09.09.2007-13.09.2007 country PT reportyear 2008 RIV BD permalink http://hdl.handle.net/11104/0148268 arlyear 2007 mrcbU63 cav_un_epca*0085843 Artificial Neural Networks - ICANN 2007 Part I. 3-540-74693-5 129 138 Berlin Springer 2007 Lecture Notes in Computer Scinece 4669 SL 1 - Theoretical Computer Science and General Issues mrcbU67 Marques de Sá J. 340 mrcbU67 Alexandre L. A. 340 mrcbU67 Duch W. 340 mrcbU67 Mandic D. 340