responsible-ai-toolbox and responsibly
These are complements rather than competitors: Microsoft's Responsible AI Toolbox provides broader model interpretability and data exploration capabilities, while Responsibly specializes in targeted bias auditing and mitigation techniques that can be integrated into a comprehensive fairness assessment workflow.
About responsible-ai-toolbox
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
The Responsible AI Toolbox helps AI developers and stakeholders evaluate and understand their machine learning models. It takes your trained AI model and its associated data, then provides interactive dashboards to visualize model errors, fairness issues across different user groups, and explanations for individual predictions. This suite of tools is for anyone building, deploying, or overseeing AI systems who needs to ensure their models are fair, transparent, and performing as expected.
About responsibly
ResponsiblyAI/responsibly
Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰
This toolkit helps data scientists, machine learning practitioners, and researchers evaluate and address unfairness in their AI systems. You input your machine learning models and data, and it outputs insights into potential biases and offers tools to make your models fairer. It's especially useful for those building classification models or working with natural language processing.
Scores updated daily from GitHub, PyPI, and npm data. How scores work