hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hudson (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAMA-791) Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes
Date Wed, 07 Aug 2013 04:43:48 GMT

    [ https://issues.apache.org/jira/browse/HAMA-791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13731629#comment-13731629
] 

Hudson commented on HAMA-791:
-----------------------------

SUCCESS: Integrated in Hama trunk #152 (See [https://builds.apache.org/job/Hama%20trunk/152/])
HAMA-791: Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes
(yxjiang: rev 1511164)
* /hama/trunk/CHANGES.txt
* /hama/trunk/ml/src/test/java/org/apache/hama/ml/perception/TestSmallMultiLayerPerceptron.java

                
> Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes
> ------------------------------------------------------------------------------------
>
>                 Key: HAMA-791
>                 URL: https://issues.apache.org/jira/browse/HAMA-791
>             Project: Hama
>          Issue Type: Bug
>            Reporter: Yexi Jiang
>            Assignee: Yexi Jiang
>              Labels: machine_learning
>             Fix For: 0.6.3
>
>         Attachments: HAMA-791.patch
>
>
> Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes.
If the weights of MLP initialized to very bad values, the model might fail the test.
> Since the new model developed in [HAMA-770|https://issues.apache.org/jira/browse/HAMA-770]
will replace the current old model, this problem will be simply fixed by increase the training
iteration.

--
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

Mime
View raw message