Difference between revisions of "Publications:Selecting variables for neural network committees"
From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Marija Bacauskiene, Vladas Cibulskis, Antanas Verikas |PID=239219 |Name=Bac...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Marija Bacauskiene, Vladas Cibulskis, Antanas Verikas | {{PublicationSetupTemplate|Author=Marija Bacauskiene, Vladas Cibulskis, Antanas Verikas | ||
|PID=239219 | |PID=239219 | ||
| − | |Name=Bacauskiene, Marija (Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania);Cibulskis, Vladas (Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania);Verikas, Antanas | + | |Name=Bacauskiene, Marija (Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania);Cibulskis, Vladas (Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania);Verikas, Antanas (av) (0000-0003-2185-8973) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), Intelligenta system (IS-lab) (3941)) |
|Title=Selecting variables for neural network committees | |Title=Selecting variables for neural network committees | ||
|PublicationType=Conference Paper | |PublicationType=Conference Paper | ||
| Line 40: | Line 40: | ||
|Projects= | |Projects= | ||
|Notes= | |Notes= | ||
| − | |Abstract=<p>The aim of the variable selection is threefold: to reduce model complexity, to promote diversity of committee networks, and to find a trade-off between the accuracy and diversity of the networks. To achieve the goal, the steps of neural network training, aggregation, and elimination of irrelevant input variables are integrated based on the negative correlation learning | + | |Abstract=<p>The aim of the variable selection is threefold: to reduce model complexity, to promote diversity of committee networks, and to find a trade-off between the accuracy and diversity of the networks. To achieve the goal, the steps of neural network training, aggregation, and elimination of irrelevant input variables are integrated based on the negative correlation learning (1) error function. Experimental tests performed on three real world problems have shown that statistically significant improvements in classification performance can be achieved from neural network committees trained according to the technique proposed.</p> |
|Opponents= | |Opponents= | ||
|Supervisors= | |Supervisors= | ||
| Line 55: | Line 55: | ||
|CreatedDate=2008-10-06 | |CreatedDate=2008-10-06 | ||
|PublicationDate=2008-10-06 | |PublicationDate=2008-10-06 | ||
| − | |LastUpdated= | + | |LastUpdated=2014-11-10 |
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239219}} | |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239219}} | ||
<div style='display: none'> | <div style='display: none'> | ||
Latest revision as of 21:40, 30 September 2016
| Title | Selecting variables for neural network committees |
|---|---|
| Author | Marija Bacauskiene and Vladas Cibulskis and Antanas Verikas |
| Year | 2006 |
| PublicationType | Conference Paper |
| Journal | |
| HostPublication | Advances in neural networks - ISNN 2006 : third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 ; proceedings. I |
| Conference | third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 |
| DOI | http://dx.doi.org/10.1007/11759966_123 |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:239219 |
| Abstract | The aim of the variable selection is threefold: to reduce model complexity, to promote diversity of committee networks, and to find a trade-off between the accuracy and diversity of the networks. To achieve the goal, the steps of neural network training, aggregation, and elimination of irrelevant input variables are integrated based on the negative correlation learning (1) error function. Experimental tests performed on three real world problems have shown that statistically significant improvements in classification performance can be achieved from neural network committees trained according to the technique proposed. |
