Build Responsible AI using Error Analysis toolkit

From the creator

Error Analysis, a new Responsible AI open source toolkit, enables machine learning practitioners to identify model errors and diagnose the root causes behind these errors, helping to build responsible, reliable, and trusted solutions. Jump to: [00:00] Livestream begins [01:24] About AI models [02:37] Error analysis [04:23] Interpretability and fairness [06:34] About Error Analysis toolkit [11:46] Error explorer demo [22:18] Debugging demos - Global and Local explanations Learn more: Blog on Microsoft Tech Community: https://aka.ms/AIShow/RAIBlog Website: https://aka.ms/AIShow/RAISite Readme: https://aka.ms/AIShow/EAD Sample notebook: https://aka.ms/AIShow/Notebooks/EA Create a free account (Azure) https://aka.ms/aishow-seth-azurefree Don't miss new episodes, subscribe to the AI Show - https://aka.ms/aishowsubscribe Join us every other Friday for an AI Show livestream on Learn TV and YouTube - https://aka.ms/LearnTV, https://aka.ms/AIShowLive

Published 2021-03-01 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.