dylan-slack/Modeling-Uncertainty-Local-Explainability
Local explanations with uncertainty 💐!
When you rely on AI for important decisions, understanding why a model makes a specific prediction is crucial. This project provides a way to see not just which parts of an input (like an image or customer data) influenced a decision, but also how certain the AI is about those influences. It takes an existing AI model's prediction and its input to show you the key factors and the confidence level, helping anyone who needs to trust and explain AI choices, such as risk analysts or image classifiers.
No commits in the last 6 months.
Use this if you need to understand the individual reasons behind an AI's specific prediction and gauge the reliability of those explanations for critical decisions.
Not ideal if you are looking for general insights into how your entire AI model works across all predictions, rather than detailed explanations for individual cases.
Stars
42
Forks
14
Language
Python
License
MIT
Last pushed
Aug 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dylan-slack/Modeling-Uncertainty-Local-Explainability"
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...