dc.contributor.author |
Krimpenis, A |
en |
dc.contributor.author |
Vosniakos, G |
en |
dc.date.accessioned |
2014-03-01T02:49:57Z |
|
dc.date.available |
2014-03-01T02:49:57Z |
|
dc.date.issued |
2005 |
en |
dc.identifier.uri |
https://dspace.lib.ntua.gr/xmlui/handle/123456789/34816 |
|
dc.relation.uri |
http://www.informatik.uni-trier.de/~ley/db/conf/esann/esann2005.html#KrimpenisV05 |
en |
dc.relation.uri |
http://www.dice.ucl.ac.be/Proceedings/esann/esannpdf/es2005-21.pdf |
en |
dc.subject |
Artificial Neural Network |
en |
dc.subject |
Experimental Data |
en |
dc.subject |
Model Building |
en |
dc.subject |
Multiple Linear Regression |
en |
dc.subject |
Training Algorithm |
en |
dc.title |
Initialisation improvement in engineering feedforward ANN models |
en |
heal.type |
conferenceItem |
en |
heal.publicationDate |
2005 |
en |
heal.abstract |
Any feedforward artificial neural network (ANN) training procedure begins with the initialisation of the connection weights' values. These initial values are generally selected in a random or quasi-random way in order to increase training speed. Nevertheless, it is common practice to initialize the same ANN architecture in a repetitive way in order for satisfactory training results to be achieved. This |
en |
heal.journalName |
The European Symposium on Artificial Neural Networks |
en |