horn-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Edward J. Yoon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HORN-21) Implement dropout for training
Date Sun, 29 May 2016 23:51:12 GMT

    [ https://issues.apache.org/jira/browse/HORN-21?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15306116#comment-15306116
] 

Edward J. Yoon commented on HORN-21:
------------------------------------

This web page is well describes about dropout https://www.quora.com/How-do-you-implement-a-dropout-in-deep-neural-networks

According to theory, formula is different, between training and test mode. so, something like
isTraining() that checks whether training or not should be provided within Neuron object.
I'll add this feature when I push my local changes.

> Implement dropout for training
> ------------------------------
>
>                 Key: HORN-21
>                 URL: https://issues.apache.org/jira/browse/HORN-21
>             Project: Apache Horn
>          Issue Type: New Feature
>          Components: api
>            Reporter: Minho Kim
>
> http://arxiv.org/pdf/1207.0580.pdf
> Dropout is a relatively algorithm which appears to be highly effective for improving
the quality of neural network. It is a vital feature in almost neural network implementation.



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

Mime
View raw message