Machine learning models can be difficult to debug, as they are often treated as black boxes that provide only limited visibility into their true accuracy. Additionally, traditional performance techniques often have a blind spot when it comes to identifying model or data errors, which can lead to fairness or societal bias issues.

The need for transparency in machine learning is increasingly important, as certain industries require the ability to understand or explain the features that drove a model’s outcome. This is where Azure Machine Learning’s Responsible AI dashboard comes in.

This workshop is designed to give participants a hands-on learning experience with the Responsible AI dashboard, specifically in the areas of Error Analysis, Data Analysis, and Explainability/Interpretability. By the end of the workshop, participants will have gained valuable insights and best practices for using the Azure Responsible AI dashboard to produce AI solutions that are less harmful and more trustworthy.