Yu-Group/adaptive-wavelets

Adaptive, interpretable wavelets across domains (NeurIPS 2021)

41
/ 100
Emerging

This project helps scientists and researchers distill complex deep learning models into simpler, more interpretable wavelet transforms. You provide raw data, optionally with a pre-trained neural network, and it outputs a more compact, faster, and explainable model that captures the essential information using adaptive wavelets. This is designed for domain experts who need to understand why a model makes certain predictions.

No commits in the last 6 months.

Use this if you need to simplify an existing neural network model or analyze raw data to extract interpretable, multi-scale features for scientific discovery or critical decision-making.

Not ideal if your primary goal is to solely maximize predictive performance without needing model interpretability or efficiency gains.

scientific-modeling data-compression model-interpretability cosmology molecular-biology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

83

Forks

14

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 30, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Yu-Group/adaptive-wavelets"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.