ESB neural-networks-based classifiers

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F12%3AA13017K2" target="_blank" >RIV/61988987:17310/12:A13017K2 - isvavai.cz</a>
Výsledek na webu
<a href="http://projects.osu.eu/intsys/software/esb_nnclass.html" target="_blank" >http://projects.osu.eu/intsys/software/esb_nnclass.html</a>
DOI - Digital Object Identifier
—

Jazyk výsledku
angličtina
Název v původním jazyce
ESB neural-networks-based classifiers
Popis výsledku v původním jazyce
In this software we demonstrate an experimental study which was aimed to explore the possibility of using neural network as the base algorithms for so called weak classifiers. In our experiment neural networks went only through one adaptation cycle. We have generated experimental ensembles of 100 weak classifiers based on five types of neural networks. A total of 3,240 of such ensembles have been created and tested. We have proposed filtering of input as the new diversity-achieving method. We have tested this method in common with two others methods. The experiment has been conducted over the MNIST database.
Název v anglickém jazyce
ESB neural-networks-based classifiers
Popis výsledku anglicky
In this software we demonstrate an experimental study which was aimed to explore the possibility of using neural network as the base algorithms for so called weak classifiers. In our experiment neural networks went only through one adaptation cycle. We have generated experimental ensembles of 100 weak classifiers based on five types of neural networks. A total of 3,240 of such ensembles have been created and tested. We have proposed filtering of input as the new diversity-achieving method. We have tested this method in common with two others methods. The experiment has been conducted over the MNIST database.

Rok uplatnění
2012
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)