Machine Fairness – How to assess AI system’s fairness and mitigate any observed unfairness issues

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.

picture.png

 

This article will focus on AI fairness, by explaining the following aspects and tools:

  1. Fairlearn: a tool to assess AI system’s fairness and mitigate any observed unfairness issues
  2. How to use Fairlearn in Azure Machine Learning
  3. What we mean by fairness
  4. Fairlearn algorithms
  5. Fairlearn dashboard
  6. Comparing multiple models
  7. Additional resources and how to contribute

Read the full article: www.aka.ms/Fairlearn-build2020 

REMEMBER: these articles are REPUBLISHED. Your best bet to get a reply is to follow the link at the top of the post to the ORIGINAL post! BUT you're more than welcome to start discussions here:

This site uses Akismet to reduce spam. Learn how your comment data is processed.