[
https://issues.apache.org/jira/browse/HAMA-760?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yexi Jiang updated HAMA-760:
----------------------------
Attachment: HAMA-760.patch
I have added the new features as well as the corresponding test cases.
Since I didn't touch any code other than the ones in ml package, I only tested
the ml package.
The following is the output.
[INFO] Apache Hama parent POM ............................ SUCCESS [0.974s]
[INFO] core .............................................. SUCCESS [3.188s]
[INFO] graph ............................................. SUCCESS [0.584s]
[INFO] machine learning .................................. SUCCESS [34.567s]
[INFO] examples .......................................... SUCCESS [0.469s]
[INFO] yarn .............................................. SUCCESS [1.622s]
[INFO] hama-dist ......................................... SUCCESS [0.011s]
[INFO] ------------------------------------------------------------------------
[INFO] BUILD SUCCESS
[INFO] ------------------------------------------------------------------------
[INFO] Total time: 41.966s
[INFO] Finished at: Sun Jun 09 17:42:33 EDT 2013
[INFO] Final Memory: 27M/981M
> Add new features to existing Multi Layer Perceptron
> ---------------------------------------------------
>
> Key: HAMA-760
> URL: https://issues.apache.org/jira/browse/HAMA-760
> Project: Hama
> Issue Type: New Feature
> Reporter: Yexi Jiang
> Assignee: Yexi Jiang
> Labels: features, machine_learning, mlp
> Attachments: HAMA-760.patch
>
>
> Current MultiLayerPerceptron has only implemented the basic features of a
> Multi Layer Perceptron.
> There are still several features need to be implemented.
> In the next step the following features should be added:
> 1) add more cost functions such as cross entropy.
> 2) add momentum and regularization.
> 3) make the training method in MLP be public to allow user to use MLP in a
> standalone algorithm.
> 4) add more test cases on other applications, at least one with regression
> and one with classification.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
