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-10) Implement convolutional neural network based on Neuron-centric
Date Fri, 13 Nov 2015 05:36:10 GMT

    [ https://issues.apache.org/jira/browse/HORN-10?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15003584#comment-15003584
] 

Edward J. Yoon commented on HORN-10:
------------------------------------

Suppose that the input X = [5*5*3]. Suppose further that we use 1 padding (P=1), that the
filter size is F=3, and that the stride is S=2:

{code}
Input X:
0 0 0 0 0 0 0
0 2 1 0 1 1 0
0 2 1 1 1 2 0
0 1 2 1 1 0 0
0 1 2 2 2 0 0 
0 1 1 1 1 2 0
0 0 0 0 0 0 0

Filter w0:
0 -1 -1
-1 0 -1
0 0 0
{code}

Input layer has 75 neurons, and then C1 layer will have 18 neurons. Each neuron of C1 layer
calculates output activation by dot with filter, summing it up.

> Implement convolutional neural network based on Neuron-centric
> --------------------------------------------------------------
>
>                 Key: HORN-10
>                 URL: https://issues.apache.org/jira/browse/HORN-10
>             Project: Apache Horn
>          Issue Type: New Feature
>            Reporter: Edward J. Yoon
>            Assignee: Edward J. Yoon
>




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

Mime
View raw message