hslyu/GIF
Official implementation of "Deeper Understanding of Black-box Predictions via Generalized Influence Functions".
This project helps machine learning engineers and researchers understand why a complex AI model made a specific prediction. You input a 'black-box' model and a data point, and it tells you which training data points were most influential in that particular prediction. This is for AI practitioners who need to explain model behavior.
No commits in the last 6 months.
Use this if you need to explain individual predictions of your AI models by identifying the most influential training data.
Not ideal if you're looking for a general model debugging tool or a way to improve model accuracy directly.
Stars
9
Forks
—
Language
Jupyter Notebook
License
MIT
Last pushed
Dec 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hslyu/GIF"
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...