[
https://issues.apache.org/jira/browse/SINGA-10?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14899906#comment-14899906
]
wangwei commented on SINGA-10:
------------------------------
Pls refer to the README.md file under examples/rnnlm folder for instructions of
running the rnnlm model.
http://singa.apache.org/docs/rnn.html has more details on the implementation.
Need to optimize the training speed!
> 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)
