singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF subversion and git services (JIRA)" <>
Subject [jira] [Commented] (SINGA-10) Add Support for Recurrent Neural Networks (RNN)
Date Sun, 20 Sep 2015 12:37:04 GMT


ASF subversion and git services commented on SINGA-10:

Commit 79a241c8bb6c520979d52c895f4958c2b901cd47 in incubator-singa's branch refs/heads/master
from wang sheng
[;h=79a241c ]

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

improve extract_cluster function in
  - we read the last occurrence of "cluster"
  - content are the first occurrence of "{" and "}" after "cluster"
format rnnlm.h and

> Add Support for Recurrent Neural Networks (RNN)
> -----------------------------------------------
>                 Key: SINGA-10
>                 URL:
>             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

View raw message