Explainable AI, tools and frameworks to deploy interpretable and inclusive machine learning models, Google Inc., Mountain View, California, USA

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 Cao 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.

Click to expand...