29:52Improving the Fairness and Reliability of AI Solutions
From the creator
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. Join the Cloud Skills Challenge: https://aka.ms/gaidd/challenge
Published 2022-10-31 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.
Keep exploring Learn to Code
29:52
04:07
11:04"Anti-Slop" Designs with Impeccable (a Crash Course) #5 - Enable Image Generation
Net Ninja
2:25:40
42:55Java Graphics Programming Tutorial - How To Draw Shapes, Paths, Curves, and Apply Transformations
choobtorials
08:10
18:31