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

Jump to bottom

time_b? #17

Open

KPEKEP opened this issue May 24, 2024 · 1 comment

KPEKEP commented May 24, 2024

Hello!
First of all thank you for such an interesting work!
I have a couple questions:

Could you please elaborate how did you come from this formulae

to having extra term time_b? Where does it come from and what is it's meaning?

CfC/torch_cfc.py

Line 139 in 3ebaa03

t_b = self.time_b(x)

From my understanding, in minimal case of Cfc model, x0 is assumed to be zero:
https://github.com/fullerf/LightningCfC/blob/6dc15040c5a003ae837bcbf24ddda45dd99f8cff/src/LightningCfC/torch_cfc.py#L129
It it always the case though? And is it safe assumption to make?

Thanks, looking forward to your response.

Author

KPEKEP commented May 24, 2024

I wonder, if time_b is approximation of w_tau, then why it is not multiplied by time when calculating sigma?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment