Yu-Group/adaptive-wavelets
Adaptive, interpretable wavelets across domains (NeurIPS 2021)
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.
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.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...