Neuromorphic features of probabilistic neural networks
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F07%3A00090278" target="_blank" >RIV/67985556:_____/07:00090278 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Neuromorphic features of probabilistic neural networks
Original language description
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 productcomponents. 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 formulafor 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 ofinvolved variables.
Czech name
Neuromorfní vlastnosti pravděpodobnostních neuronových sítí
Czech description
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.
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)<br>R - Projekt Ramcoveho programu EK
Others
Publication year
2007
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Kybernetika
ISSN
0023-5954
e-ISSN
—
Volume of the periodical
43
Issue of the periodical within the volume
5
Country of publishing house
CZ - CZECH REPUBLIC
Number of pages
16
Pages from-to
697-712
UT code for WoS article
—
EID of the result in the Scopus database
—