Group Abstract Group Abstract

Message Boards Message Boards

0
|
148 Views
|
2 Replies
|
0 Total Likes
View groups...
Share
Share this post:

How to implement a normalization layer that does not exponentiate (like softmax)?

Posted 1 day ago

It should sum up all the elements from an input vector and just divide each one by that sum. Assume all elements are positive.

POSTED BY: Iuval Clejan
2 Replies
Posted 23 hours ago

Yes, exactly! Thanks for your patience while I get up to speed.

POSTED BY: Iuval Clejan

You mean something like this?

NetGraph[
 <|"norm" -> AggregationLayer[Total, 1], 
  "divide" -> ThreadingLayer[Divide, -1]|>,
 {NetPort["Input"] -> "norm", {NetPort["Input"], "norm"} -> "divide"}
 ]
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard