hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Edward J. Yoon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAMA-681) Multi Layer Perceptron
Date Mon, 03 Jun 2013 05:18:19 GMT

    [ https://issues.apache.org/jira/browse/HAMA-681?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13672828#comment-13672828
] 

Edward J. Yoon commented on HAMA-681:
-------------------------------------

Thanks, Yexi. I'll look at tonight when I get home. 

{quote}
Note:
This version of MLP is the basic version, I will add more features if this one passes the
review.
BTW, I have checked out hama from Apache svn repository. Since I don't have permission, I
cannot create any branch.
{quote}

You have to follow the 'HowToContribute' development process[1] until you become a full fledge
committer. Of course, if you have different idea about coding conventions, Please feel free
to open the discuss or vote thread on dev@ list. This will help you learn something interesting
or exciting. :)

1. https://wiki.apache.org/hama/HowToContribute
                
> Multi Layer Perceptron 
> -----------------------
>
>                 Key: HAMA-681
>                 URL: https://issues.apache.org/jira/browse/HAMA-681
>             Project: Hama
>          Issue Type: New Feature
>          Components: machine learning
>            Reporter: Christian Herta
>            Assignee: Yexi Jiang
>              Labels: patch, perceptron
>         Attachments: HAMA-681.patch, perception.patch
>
>
> Implementation of a Multilayer Perceptron (Neural Network)
>  - Learning by Backpropagation 
>  - Distributed Learning
> The implementation should be the basis for the long range goals:
>  - more efficent learning (Adagrad, L-BFGS)
>  - High efficient distributed Learning
>  - Autoencoder - Sparse (denoising) Autoencoder
>  - Deep Learning
>  
> ---
> Due to the overhead of Map-Reduce(MR) MR didn't seem to be the best strategy to distribute
the learning of MLPs.
> Therefore the current implementation of the MLP (see MAHOUT-976) should be migrated to
Hama. First all dependencies to Mahout (Matrix-Library) must be removed to get a standalone
MLP Implementation. Then the Hama BSP programming model should be used to realize distributed
learning.
> Different strategies of efficient synchronized weight updates has to be evaluated.
> Resources:
>  Videos:
>     - http://www.youtube.com/watch?v=ZmNOAtZIgIk
>     - http://techtalks.tv/talks/57639/
>  MLP and Deep Learning Tutorial:
>  - http://www.stanford.edu/class/cs294a/
>  Scientific Papers:
>  - Google's "Brain" project: 
> http://research.google.com/archive/large_deep_networks_nips2012.html
>  - Neural Networks and BSP: http://ipdps.cc.gatech.edu/1998/biosp3/bispp4.pdf
>  - http://jmlr.csail.mit.edu/papers/volume11/vincent10a/vincent10a.pdf

--
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