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

Add Phasor layers/network capability #13

Open
kmheckel opened this issue Oct 23, 2023 · 1 comment
Open

Add Phasor layers/network capability #13

kmheckel opened this issue Oct 23, 2023 · 1 comment
Labels
enhancement New feature or request

Comments

@kmheckel
Copy link
Owner

It would be awesome to implement the ability to train spiking phasor networks in Spyx. JAX has the ability to support complex-valued autodifferentiation, so this should be possible. Doing this would enable extremely fast training by eliminating recurrence when learning before converting to a recurrent architecture for inference.

https://arxiv.org/abs/2204.00507

@kmheckel kmheckel added the enhancement New feature or request label Oct 23, 2023
@kmheckel
Copy link
Owner Author

kmheckel commented Feb 8, 2024

This is tied to the implementation of latency based training tools/objectives. #21

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant