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

New layers and adaptive lambdas #23

Closed

SuperSashka opened this issue Mar 8, 2023 · 2 comments · Fixed by #32

Assignees

Milestone

Member

SuperSashka commented Mar 8, 2023 •

edited

Loading

For some applications that are usually concerning with high-frequency oscillations, we need Fourier layers and kernel weights loss normalization

SuperSashka added this to the Better quality milestone

Member Author

SuperSashka commented Mar 10, 2023

For adaptive weights there are two appaoaches - tangent kernel https://arxiv.org/pdf/2007.14527.pdf and dispersion assessment https://arxiv.org/pdf/2302.12697.pdf .
For Fourier layers there are also several approaches as an example https://arxiv.org/pdf/2012.10047.pdf, https://docs.nvidia.com/deeplearning/modulus/user_guide/theory/advanced_schemes.html

SuperSashka assigned nikiniki1

Member Author

SuperSashka commented Jun 13, 2023

Layers are merged with #30

SuperSashka linked a pull request

that will close this issue

Adaptive lambdas #32

Merged

nikiniki1 closed this as completed in #32

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