Trusted-AI/AIX360
Interpretability and explainability of data and machine learning models
This toolkit helps data scientists, machine learning engineers, and researchers understand why their AI models make specific predictions. It takes your existing tabular, text, image, or time-series data and machine learning models, and outputs explanations showing the factors influencing the model's decisions or highlighting important aspects of the data itself. This allows you to build trust in AI systems and debug potential issues.
1,767 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to explain the decisions of your machine learning models to stakeholders, debug unexpected model behavior, or gain insights into your data's patterns.
Not ideal if you are looking for a simple, one-click solution for basic model predictions, as it requires a good understanding of machine learning concepts and interpretability methods.
Stars
1,767
Forks
328
Language
Python
License
Apache-2.0
Last pushed
Feb 26, 2025
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Trusted-AI/AIX360"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
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...