-
Notifications
You must be signed in to change notification settings - Fork 615
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
Add Echo State Network (ESN) layer #1862
Add Echo State Network (ESN) layer #1862
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @pedrolarben Sorry for the late reply. I have some comments here. Please check it out.
cc @qlzh727
tensorflow_addons/layers/esn.py
Outdated
H. Jaeger | ||
"The "echo state" approach to analysing and training recurrent neural networks". | ||
GMD Report148, German National Research Center for Information Technology, 2001. | ||
https://www.researchgate.net/publication/215385037 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could we use the hyperlink here? Like xxx.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@WindQAQ Thanks for your review :)
Do you mean something like this?
Option A:
This is based on the paper
H. Jaeger
["The "echo state" approach to analysing and training recurrent neural networks".
GMD Report148, German National Research Center for Information Technology, 2001.]
(https://www.researchgate.net/publication/215385037)
Option B:
This is based on the [paper](https://www.researchgate.net/publication/215385037)
H. Jaeger
"The "echo state" approach to analysing and training recurrent neural networks".
GMD Report148, German National Research Center for Information Technology, 2001.
Option C:
This is based on the paper
H. Jaeger
["The "echo state" approach to analysing and training recurrent neural networks"]
(https://www.researchgate.net/publication/215385037).
GMD Report148, German National Research Center for Information Technology, 2001.
I think I prefer option C, please let me know your opinion
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@pedrolarben I prefer C too :-)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done! 👍
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for the contribution!
* Added Echo State Network (ESN) layer * removed super arguments * removed constant argument from esn call * Changed test name esn layer * Added hyperlink to esn docs
* Added Echo State Network (ESN) layer * removed super arguments * removed constant argument from esn call * Changed test name esn layer * Added hyperlink to esn docs
Part of #1809.
After adding the ESN recurrent cell #1811, here it is the ESN layer.