Explainable AI (XAI) Frameworks
- 01. What-If Tool - Visually probe the behavior of trained machine learning models, with minimal coding.
- 02. DeepLIFT: Deep Learning Important FeaTures
- 03. Local Interpretable Model-Agnostic Explanations (LIME) — Explaining the predictions of any machine learning classifier
- 04. SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model.
- 05. Rulex Platform’s machine learning capabilities ensure not only essential transparency but also peak performance and unwavering accuracy throughout the entire forecasting process.
- 06. Activation Atlases - A new technique for visualizing what interactions between neurons can represent.
- 07. This XAI Framework allows you to introduce explainability and perform bias evaluation in AI systems by going beyond algorithms using a tool+process approach.
- 08. ELI5 is a Python library which allows to visualize and debug various Machine Learning models using unified API.
- 09. InterpretML - A toolkit to help understand models and enable responsible machine learning
- 10. OmniXAI (Omni eXplainable AI) is a Python ML library for XAI, offering omni-way explainable AI and interpretable ML capabilities to address many pain points in explaining decisions made by ML models
- 11. Shapash is a Python library designed to make machine learning interpretable and accessible to everyone. It offers various visualization types with clear and explicit labels that are easy to understand.
- 12. Quantitative Testing with Concept Activation Vectors (TCAV) is a new interpretability method to understand what signals your neural networks models uses for prediction.
- 13. The DALEX package xrays any model and helps to explore and explain its behaviour, helps to understand how complex models are working.
- 14. Alibi Explain is an open source Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-quality implementations of black-box, white-box, local and global explanation methods for classification and regression models.
- 15. explainerdashboard is a library for quickly building interactive dashboards for analyzing and explaining the predictions and workings of (scikit-learn compatible) machine learning models, including xgboost, catboost and lightgbm.