Skip to content
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

Implementation of Long Short term memory block #144

Open
mikerabat opened this issue Jan 23, 2025 · 2 comments
Open

Implementation of Long Short term memory block #144

mikerabat opened this issue Jan 23, 2025 · 2 comments

Comments

@mikerabat
Copy link

It would be great to have a LSTM layer. Many other libraries support them out of the box so it would be great to have them; )

It would also greatly support my work on ECG beat classification - I think they could make a difference there...

Thank you :)

@joaopauloschuler
Copy link
Owner

Hi @mikerabat ,
Is the ECG beat classification project open source? If not, does it have a web site?

Although we don't have LSTM, we do have a transformer decoder block that is considered by many as a superior solution:
https://github.com/joaopauloschuler/neural-api/tree/master/examples/SimpleNLP
https://voidful.medium.com/why-transformer-faster-then-lstm-on-generation-c3f30977d747
https://ai.stackexchange.com/questions/20075/why-does-the-transformer-do-better-than-rnn-and-lstm-in-long-range-context-depen

Kind regards,
JP.

@mikerabat
Copy link
Author

Sorry no... there is no website. It's research for the company I work for..
Many thanks for the links! I will asop check the links :)

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

No branches or pull requests

2 participants