Skip to content

no nonlinearity in z #149

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 18, 2016
Merged

no nonlinearity in z #149

merged 1 commit into from
Mar 18, 2016

Conversation

kyunghyuncho
Copy link
Contributor

z is a pre-activation, and \sigma should not be there. @hongkunyoo

@@ -174,7 +174,7 @@ be computed with :

.. math::

z = \sigma(W x_t + U h_{t-1} + b)
z = W x_t + U h_{t-1} + b
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you double check that the code do that? I think so, but I could have looked at the wrong place in the code.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The code for computing z looks like this:

preact = tensor.dot(h_, tparams[_p(prefix, 'U')])
preact += x_
https://github.com/lisa-lab/DeepLearningTutorials/blob/master/code/lstm.py#L175-L176

nouiz added a commit that referenced this pull request Mar 18, 2016
@nouiz nouiz merged commit 7768809 into lisa-lab:master Mar 18, 2016
@nouiz
Copy link
Member

nouiz commented Mar 18, 2016

thanks

taneishi pushed a commit to taneishi/DBN that referenced this pull request Nov 28, 2019
taneishi pushed a commit to taneishi/DBN that referenced this pull request Feb 13, 2020
no nonlinearity in z

Former-commit-id: ea169ec
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants