This post has been republished via RSS; it originally appeared at: New blog articles in Microsoft Tech Community.
As we are leveraging data for making significant decisions that affect individual lives in domains such as health care, justice, finance, education, marketing, and employment, it is important to ensure the safe, ethical, and responsible use of AI. In collaboration with the Aether Committee and its working groups, Microsoft is bringing the latest research in responsible AI to Azure: these new responsible ML capabilities in Azure Machine Learning and our open source toolkits, empower data scientists and developers to understand machine learning models, protect people and their data, and control the end-to-end machine learning process.
This article will focus on AI fairness, by explaining the following aspects and tools:
- Fairlearn: a tool to assess AI system’s fairness and mitigate any observed unfairness issues
- How to use Fairlearn in Azure Machine Learning
- What we mean by fairness
- Fairlearn algorithms
- Fairlearn dashboard
- Comparing multiple models
- Additional resources and how to contribute
Read the full article: www.aka.ms/Fairlearn-build2020