Recurrent Bayesian Reasoning in Probabilistic Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F07%3A00085844" target="_blank" >RIV/67985556:_____/07:00085844 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Recurrent Bayesian Reasoning in Probabilistic Neural Networks
Original language description
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 canbe ``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.
Czech name
Rekurentní bayesovské odvozování v pravděpodobnostních neuronových sítích
Czech description
Rekurentní bayesovské odvozování v pravděpodobnostních neuronových sítích

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

Publication year
2007
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)