Re: Some questions about Random Committee classifier in Weka

>   We are students from Nanjing University of Aeronautics and Astronautics in China. It's a great honor to have software like Weka to help us with machine learning. However, during the data processing, we had some questions about the principle of the Random Committee classifier. After reading the Weka manual and related papers in recent years, we have solved some of them. But there are still two questions we want to ask for help：
>   （1）In the Random Committee classifier, which sub-classifiers participate in the component committee process? We may need a list of classifiers.

By default, RandomTree is being used. But the user can choose another
base classifier, as long as that one implements the
weka.core.Randomizable interface:
https://weka.sourceforge.io/doc.dev/weka/core/Randomizable.html

"numIterations" defines the size of the committee, i.e., the number of
copies of the base classifier that are generated. Each of the copies
gets trained on the same training data but with a different random
seed.

>   （2）How does the random committee classifier implement data encoding?

Can you explain what you mean by "data encoding"?

Cheers, Peter
-- 
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
https://www.cs.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/
_______________________________________________
Wekalist mailing list -- [email protected]
Send posts to [email protected]
To unsubscribe send an email to [email protected]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html