bibtype	J - Journal Article
ARLID	0090278
utime	20240903170617.2
mtime	20071127235959.9
title (primary) (eng)	Neuromorphic features of probabilistic neural networks
specification	page_count 16 s.
serial	ARLID cav_un_epca*0297163 ISSN 0023-5954 title Kybernetika volume_id 43 volume 5 (2007) page_num 697-712 publisher name Ústav teorie informace a automatizace AV ČR, v. v. i.
title (cze)	Neuromorfní vlastnosti pravděpodobnostních neuronových sítí
keyword	probabilistic neural networks
keyword	distribution mixtures
keyword	sequential EM algorithm
keyword	pattern recognition
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.
cas_special	project project_id 507752 country XE agency EC ARLID cav_un_auth*0200689 project project_id GA102/07/1594 agency GA ČR ARLID cav_un_auth*0228611 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 research CEZ:AV0Z10750506 abstract (eng) We summarize the main results on probabilistic neural networks recently published in a series of papers. Considering the framework of statistical pattern recognition we assume approximation of class-conditional distributions by finite mixtures of product components. The probabilistic neurons correspond to mixture components and can be interpreted in neurophysiological terms. In this way we can find possible theoretical background of the functional properties of neurons. For example, the general formula for synaptical weights provides a statistical justification of the well known Hebbian principle of learning. Similarly, the mean effect of lateral inhibition can be expressed by means of a formula proposed by Perez as a measure of dependence tightness of involved variables. abstract (cze) Souhrnná práce o pravděpodobnostních neuronových sítích, které nabízejí alternativní řešení problému výběru příznaků (podprostorový přístup) a jsou široce použitelné pro řešení mnohorozměrných úloh klasifikace s omezenými datovými soubory. reportyear 2008 RIV IN mrcbC52 4 O 4o 20231122133652.2 permalink http://hdl.handle.net/11104/0151218 mrcbT16-f 0.464 mrcbT16-g 0.044 mrcbT16-h 8.9 mrcbT16-i 0.0021 mrcbT16-j 0.359 mrcbT16-k 329 mrcbT16-l 68 mrcbT16-q 21 mrcbT16-s 1.071 mrcbT16-y 14.83 mrcbT16-x 0.67 arlyear 2007 mrcbTft \nSoubory v repozitáři: 0090278.pdf mrcbU63 cav_un_epca*0297163 Kybernetika 0023-5954 Roč. 43 č. 5 2007 697 712 Ústav teorie informace a automatizace AV ČR, v. v. i.