Re: Question related to the book

Feature extraction using PrincipalComponents or MultiClassFLDA is an example of simple representation learning: these filters map the data into a new feature space (i.e., representation) that may make learning easier.

More sophisticated representation learning generally involves deep learning. Check out the wekaDeepLearning4j package for info on how to use deeplearning4j in WEKA (https://deeplearning.cms.waikato.ac.nz/). You could also use the wekaPyScript package to apply a Python-based deep learning library in a WEKA filter or classifier.

Cheers,
Eibe

> On 14/06/2021, at 6:00 PM, Edward Wiskers <[email protected]> wrote:
> 
> Hi all, 
> 
> In the last version of the book, especially on page 418, it was highlighted that Representation learning techniques transform features into some intermediate representation prior to mapping them to final predictions. 
> 
> Can any of the authors explain the idea behind Representation learning techniques? How it differs from classical machine learning and provide an example algorithm related to this category in Weka?
> 
> 
> Thanks in advance. 
> Edward
> _______________________________________________
> 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

_______________________________________________
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