Mailing-List: contact dev-help@hama.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@hama.apache.org
Date: Thu, 9 May 2013 21:49:16 +0000 (UTC)
From: "Yu Lee (JIRA)" <jira@apache.org>
To: dev@hama.apache.org
Message-ID: <JIRA.12617453.1353687279030.295211.1368136156574@arcas>
In-Reply-To: <JIRA.12617453.1353687279030@arcas>
References: <JIRA.12617453.1353687279030@arcas>
Subject: [jira] [Commented] (HAMA-681) Multi Layer Perceptron
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HAMA-681?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13653265#comment-13653265 ] 

Yu Lee commented on HAMA-681:
-----------------------------

Edward: Thanks a lot! 
I have removed the whitespace in my name as "YuLee".
However, when I tried to create a test wiki page by going to http://wiki.apache.org/hama/LeeyuTestPage?action=edit, it shows "You are not allowed to edit this page". Do you have any ideas about this?

                
> 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
>
> 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