Help with NeuralNetwork Classifier

[Vinicius Carvalho-3]

Hello there! I'm just starting with Weka (had a previous experience with matlab IA toolbox, and Joone) and I would like to test the classifier of the Weka. As I'm new to the Weka environment, I was able to load my data, and create the network (I believe that the last input is always be the result right, hence it only works for single class classifiers). After tweaking the parameters and running the classifier (I'm using the explorer, but I'll move to integration on my code soon) how do I use it to actually classify some test data? I could not find a tutorial on this, anyone could point me the right direction?

Regards

--
The intuitive mind is a sacred gift and the
rational mind is a faithful servant. We have
created a society that honors the servant and
has forgotten the gift.


_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

[Peter Reutemann-3]

> Hello there! I'm just starting with Weka (had a previous experience with
> matlab IA toolbox, and Joone) and I would like to test the classifier of the
> Weka. As I'm new to the Weka environment, I was able to load my data, and
> create the network (I believe that the last input is always be the result
> right, hence it only works for single class classifiers

Weka allows only a single class attribute in a dataset. MLP handles
numeric and nominal class attributes (with an arbitrary number of
labels). See also FAQ "Does WEKA support multi-label classification?".

> ). After tweaking the
> parameters and running the classifier (I'm using the explorer, but I'll move
> to integration on my code soon)

For integrating the classifier into your code, see FAQ "How do I use
WEKA's classes in my own code?".

> how do I use it to actually classify some
> test data? I could not find a tutorial on this, anyone could point me the
> right direction?

See FAQ "How do I make predictions with a trained model?". BTW If you
have a test set, then just use the "Supplied test set" option in the
Explorer or the -T option on the commandline.

Link to the FAQs available from the Weka homepage.

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/           Ph. [phone]

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html