h2oai/mli-resources
H2O.ai Machine Learning Interpretability Resources
This collection helps data scientists understand and explain the decisions made by complex machine learning models. It provides practical examples and resources to demystify 'black-box' models, allowing practitioners to interpret why a model made a specific prediction. The input is trained machine learning models and data, and the output is insights and explanations about model behavior, useful for justifying decisions to regulators or customers.
491 stars. No commits in the last 6 months.
Use this if you are a data scientist who needs to explain the logic of complex machine learning models to non-technical stakeholders, satisfy regulatory requirements, or build trust in your model's predictions.
Not ideal if you are solely focused on model accuracy and do not require detailed explanations or justifications for model outcomes.
Stars
491
Forks
130
Language
Jupyter Notebook
License
—
Last pushed
Dec 12, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/h2oai/mli-resources"
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...