mahout-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Suneel Marthi (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (MAHOUT-976) Implement Multilayer Perceptron
Date Fri, 20 Dec 2013 21:18:10 GMT

     [ https://issues.apache.org/jira/browse/MAHOUT-976?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Suneel Marthi updated MAHOUT-976:
---------------------------------

    Fix Version/s:     (was: Backlog)

> Implement Multilayer Perceptron
> -------------------------------
>
>                 Key: MAHOUT-976
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-976
>             Project: Mahout
>          Issue Type: New Feature
>    Affects Versions: 0.7
>            Reporter: Christian Herta
>            Assignee: Ted Dunning
>            Priority: Minor
>              Labels: multilayer, networks, neural, perceptron
>             Fix For: 0.9
>
>         Attachments: MAHOUT-976.patch, MAHOUT-976.patch, MAHOUT-976.patch, MAHOUT-976.patch
>
>   Original Estimate: 80h
>  Remaining Estimate: 80h
>
> Implement a multi layer perceptron
>  * via Matrix Multiplication
>  * Learning by Backpropagation; implementing tricks by Yann LeCun et al.: "Efficent Backprop"
>  * arbitrary number of hidden layers (also 0  - just the linear model)
>  * connection between proximate layers only 
>  * different cost and activation functions (different activation function in each layer)

>  * test of backprop by gradient checking 
>  * normalization of the inputs (storeable) as part of the model
>  
> First:
>  * implementation "stocastic gradient descent" like gradient machine
>  * simple gradient descent incl. momentum
> Later (new jira issues):  
>  * Distributed Batch learning (see below)  
>  * "Stacked (Denoising) Autoencoder" - Feature Learning
>  * advanced cost minimazation like 2nd order methods, conjugate gradient etc.
> Distribution of learning can be done by (batch learning):
>  1 Partioning of the data in x chunks 
>  2 Learning the weight changes as matrices in each chunk
>  3 Combining the matrixes and update of the weights - back to 2
> Maybe this procedure can be done with random parts of the chunks (distributed quasi online
learning). 
> Batch learning with delta-bar-delta heuristics for adapting the learning rates.    
>  



--
This message was sent by Atlassian JIRA
(v6.1.4#6159)

Mime
View raw message