You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@mxnet.apache.org by "Gaurav Gireesh (JIRA)" <ji...@apache.org> on 2018/10/06 00:39:00 UTC

[jira] [Created] (MXNET-1030) Cosine Embedding Loss Function

Gaurav Gireesh created MXNET-1030:
-------------------------------------

             Summary: Cosine Embedding Loss Function
                 Key: MXNET-1030
                 URL: https://issues.apache.org/jira/browse/MXNET-1030
             Project: Apache MXNet
          Issue Type: New Feature
          Components: Gluon
            Reporter: Gaurav Gireesh


For a target label 1 or -1, vectors target and prediction, the function computes the cosine distance between the vectors. This can be interpreted as how similar/dissimilar two input vectors are.
Can be used as a loss function while training models.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@mxnet.apache.org
For additional commands, e-mail: issues-help@mxnet.apache.org