Improving the fairness and reliability of AI solutions

AI is at the heart of technological innovations. However, it is vital that we build solutions that are more fair, trustworthy, transparent, and less harmful. This does not just have an impact on our society, but on the credibility of organizations the build or use AI as well. In this session will cover some of the best practices of debugging models through error analysis, fairness assessment, model behavior explainability and counterfactuals/what-if analysis. In addition, we will illustrate how Azure ML service simplifies how data scientists and developers can improve AI models through its easy-to-use Responsible AI (RAI) dashboard which is built on some of the best open-source tools such as Fairlearn, DICE, InterpreML, EconML etc.

Ruth Yakubu

Ruth Yakubu

Principle Cloud Advocate at Microsoft

Other sessions from: Explore the possibilities of AI

Panel: The future of AI

Panel: The future of AI

Join Eric, Erik, Ekaterina and Francesca in a panel sharing their views and...

Eric Boyd Eric Boyd
Ekaterina Marinova Ekaterina Marinova
Erik Pounds Erik Pounds
Francesca Lazzeri Francesca Lazzeri
Developer Essentials for the New Era of AI

Developer Essentials for the New Era of AI

While the arrival of AI has enabled amazing new possibilities, it has also...

Manuvir Das Manuvir Das
Azure AI innovations at Microsoft

Azure AI innovations at Microsoft

Join Eric Boyd, CVP of Azure AI, as he takes a closer look at how organiza...

Eric Boyd Eric Boyd
Beatriz Stollnitz Beatriz Stollnitz
AI skills beyond developing

AI skills beyond developing

AI is a world where IT and Business dance together. Is it enough to be a...

Ekaterina Marinova Ekaterina Marinova
Welcome to the Global AI Developer Days

Welcome to the Global AI Developer Days

Welcome to the Developer Days! Join this session and learn what is going on...

Henk Boelman Henk Boelman
Sammy Deprez Sammy Deprez
Sjoukje Zaal Sjoukje Zaal
MLOps for Continuous Learning

MLOps for Continuous Learning

MLOps empowers data scientists and app developers to help bring the machine...

Francesca Lazzeri Francesca Lazzeri