xai
Bias analysis tool
An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance
XAI - An eXplainability toolbox for machine learning
1k stars
43 watching
174 forks
Language: Python
last commit: about 3 years ago
Linked from 2 awesome lists
aiartificial-intelligencebiasbias-evaluationdownsamplingevaluationexplainabilityexplainable-aiexplainable-mlfeature-importanceimbalanceinterpretabilitymachine-learningmachine-learning-explainabilitymlupsamplingxaixai-library
altamiracorp/awesome-xaiRelated projects:
| Repository | Description | Stars |
|---|---|---|
 trusted-ai/aix360 | A toolkit for explaining complex AI models and data-driven insights | 1,633 |
 pbiecek/xai_resources | A collection of resources and papers related to Explainable Artificial Intelligence (XAI) for machine learning model interpretability. | 822 |
 h2oai/mli-resources | Provides tools and techniques for interpreting machine learning models | 484 |
 responsiblyai/responsibly | A toolkit for auditing and mitigating bias in machine learning systems | 94 |
 deel-ai/xplique | An Explainable AI toolbox that provides various methods and tools to understand and interpret the behavior of neural networks | 644 |
 interpretml/dice | Provides counterfactual explanations for machine learning models to facilitate interpretability and understanding. | 1,364 |
 andreysharapov/xaience | An online repository providing resources and information on explainable AI, algorithmic fairness, ML security, and related topics | 107 |
 jphall663/interpretable_machine_learning_with_python | Teaching software developers how to build transparent and explainable machine learning models using Python | 673 |
 dssg/aequitas | Toolkit to audit and mitigate biases in machine learning models | 694 |
 cloud-cv/evalai | A platform for comparing and evaluating AI and machine learning algorithms at scale | 1,771 |
 guildai/guildai | Automates and optimizes machine learning experiments to capture run results and improve models | 870 |
 allenai/document-qa | Tools and codebase for training neural question answering models on multiple paragraphs of text data | 434 |
| h2oai/article-information-2019 | A framework for building and evaluating machine learning systems with high accuracy and interpretability, particularly in human-centered applications. | 13 |
 understandable-machine-intelligence-lab/quantus | An eXplainable AI toolkit for evaluating and interpreting neural network explanations in various deep learning frameworks. | 556 |
 i-gallegos/fair-llm-benchmark | Compiles bias evaluation datasets and provides access to original data sources for large language models | 110 |