[jira] [Commented] (SINGA-10) Add Support for Recurrent Neural Networks (RNN)

["ASF subversion and git services (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SINGA-10?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14746815#comment-14746815 ] 

ASF subversion and git services commented on SINGA-10:
------------------------------------------------------

Commit b4a8d2b2beb077e6488569791a1581add4a957bc in incubator-singa's branch refs/heads/tutorial from [~kaiping]
[ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=b4a8d2b ]

SINGA-10 Add Support for Recurrent Neural Networks (RNN)

Add user-defined records for word (word string, word id, class id,
startpos, endpos);
Implement RnnDataLayer, WordLayer and RnnLabelLayer;
Implement create_shard.cc for the sample dataset of rnnlmlib;


> Add Support for Recurrent Neural Networks (RNN)
> -----------------------------------------------
>
>                 Key: SINGA-10
>                 URL: https://issues.apache.org/jira/browse/SINGA-10
>             Project: Singa
>          Issue Type: New Feature
>            Reporter: wangwei
>            Assignee: Zheng Kaiping
>
> The training algorithm for RNNs is Back-Propagation through time (BPTT). It is similar to the BP algorithm for feed-forward neural networks. 
> The model structures are quite different to feed-forward models. Hence,  we may need to inherit the base NeuralNet class to create a RNN class. The RNN class overrides the SetupNeurlNet function to:
> 1. parse user configuration and create the RNN graph with (circles)
> 2. broke the circles and expand it through time.
> 3. create and setup layers
> Model partitioning id not considered in this ticket.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)