AI Explainability 360

The AI Explainbability 360 toolkit is an open-source library that supports interpretability and explainability of data and machine learning models. The AI Explainability 360 Python package includes a comprehensive set of algorithms that cover different dimensions of explanations along with proxy explainability metrics.

For more information and installation instructions, see our GitHub page.

Package Reference:

• Algorithms
  • Local White Box Explainers
  • Local Black Box Explainers
  • Global White Box Explainers
  • Directly Interpretable Unsupervised Explainers
  • Directly Interpretable Supervised Explainers
  • Time Series based Local Black Box Explainers
• Metrics
• Datasets
  • CDC Dataset
  • CelebA Dataset
  • CIFAR Dataset
  • Fashion MNIST Dataset
  • HELOC Dataset
  • MEPS Dataset
  • TED Dataset
  • eSNLI Dataset

Indices and tables

• Index
• Module Index
• Search Page