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.

Sign up for GitHub

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

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion doc/lstm.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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

@nouiz nouiz Mar 18, 2016

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

@kyunghyuncho kyunghyuncho Mar 18, 2016

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


The result is then sliced to obtain the pre-nonlinearity activations for
:math:`i`, :math:`f`, :math:`\widetilde{C_t}`, and :math:`o` and the
Expand Down