Intro to Explanations for AI Platform

7 820
12
Следующее
Популярные
29 дней – 4 1178:49
How to evaluate AI applications
Опубликовано 23 апреля 2020, 23:00
In this episode of AI Adventures, we’ll show you how to use Cloud’s AI Prediction service, and how it helps you understand your model’s outputs by recognizing bias and discrepancies via AI Explanations. Yufeng also speaks to the different use cases for the two methods of feature attribution within AI Explanations - sampled shapely and integrated gradients - and what models are best suited for these attributions.

Introduction to AI Explanations for AI Platform → goo.gle/3etIcZp
AI Explainability Whitepaper → goo.gle/3ai5P3Y
AI Explanations getting started (tabular data) → goo.gle/3er2z9N
AI Explanation getting started (images) → goo.gle/2wKH7vx
Using the What-If Tool with AI Explanations → goo.gle/2KaOxLv

Check out the rest of the Cloud AI Adventures playlist → goo.gl/UC5usG
Subscribe to get all the episodes as they come out → goo.gl/S0AS51

product: Cloud AI Platform; fullname: Yufeng Guo;

#AIAdventures
автотехномузыкадетское