[jira] [Commented] (SPARK-10627) Regularization for artificial neural networks

["Ruben Janssen (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-10627?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15414040#comment-15414040 ] 

Ruben Janssen commented on SPARK-10627:
---------------------------------------

[~avulanov] That's why I asked if it would be possible to split each type of regularization in its own subtask :)
Anyway, I already made the fix for L1 and L2 regularization, but I have having some legal issues with my company as I work with ANN.

Do you have any recommendations to start off with? I already submitted a PR for a 'starters' JIRA and am waiting for clarification on [SPARK-7445]. All other tasks related to ML seem to be bigger, which I would like to address after your comment.
Thanks!

> Regularization for artificial neural networks
> ---------------------------------------------
>
>                 Key: SPARK-10627
>                 URL: https://issues.apache.org/jira/browse/SPARK-10627
>             Project: Spark
>          Issue Type: Umbrella
>          Components: ML
>    Affects Versions: 1.5.0
>            Reporter: Alexander Ulanov
>            Priority: Minor
>
> Add regularization for artificial neural networks. Includes, but not limited to:
> 1)L1 and L2 regularization
> 2)Dropout http://jmlr.org/papers/volume15/srivastava14a/srivastava14a.pdf
> 3)Dropconnect http://machinelearning.wustl.edu/mlpapers/paper_files/icml2013_wan13.pdf



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org