Source code/webpage/demos for the What-If Tool
Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training inherently transparent models and applying post-hoc explanation techniques to make machine learning predictions human-understandable. The framework distinguishes itself by integrating differential privacy into the training of interpretable models to prevent sensitive data from leaking through explanations. It also features a visualization tool for rendering interactive decision paths and model behavior. The library covers model explainability through feature importance calcu
A Python package to assess and improve fairness of machine learning models.
Algorithms for explaining machine learning models
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Die Hauptfunktionen von trusted-ai/aif360 sind: Explainability and Fairness, Explainable AI Libraries, Model Fairness And Privacy, Guardrails and AI Safety.
Open-Source-Alternativen zu trusted-ai/aif360 sind unter anderem: seldonio/alibi — Algorithms for explaining machine learning models. pair-code/what-if-tool — Source code/webpage/demos for the What-If Tool. interpretml/interpret — Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training… fairlearn/fairlearn — A Python package to assess and improve fairness of machine learning models. marcotcr/lime — This project is an agnostic model interpretability framework and explainability tool designed to provide local… aerdem4/lofo-importance — Leave One Feature Out Importance.