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-681) Multi Layer Perceptron
Date Fri, 07 Jun 2013 02:37:24 GMT

    [ https://issues.apache.org/jira/browse/HAMA-681?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13677771#comment-13677771
] 

Hudson commented on HAMA-681:
-----------------------------

Integrated in Hama-Nightly #933 (See [https://builds.apache.org/job/Hama-Nightly/933/])
    HAMA-681: Add Multi Layer Perceptron (Yexi Jiang via edwardyoon) (Revision 1490122)

     Result = SUCCESS
edwardyoon : 
Files : 
* /hama/trunk/CHANGES.txt
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/CostFunction.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/CostFunctionFactory.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/LogisticCostFunction.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/MLPMessage.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/MultiLayerPerceptron.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/PerceptronTrainer.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/Sigmoid.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SmallMLPMessage.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SmallMLPTrainer.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SmallMultiLayerPerceptron.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SquaredError.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SquashingFunction.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/SquashingFunctionFactory.java
* /hama/trunk/ml/src/main/java/org/apache/hama/ml/perception/Tanh.java
* /hama/trunk/ml/src/test/java/org/apache/hama/ml/perception
* /hama/trunk/ml/src/test/java/org/apache/hama/ml/perception/TestSmallMLPMessage.java
* /hama/trunk/ml/src/test/java/org/apache/hama/ml/perception/TestSmallMultiLayerPerceptron.java

                
> 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
>             Fix For: 0.6.2
>
>         Attachments: HAMA-681.patch, HAMA-681.patch, 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