At Fiddler.AI, we're working on cutting-edge Explainable AI Algorithms, here is our latest publication that was recently awarded the Best Paper award at CD-Make 2020. #WeekendReading #ExplainableAI #ShapleyValues
Please let us know if you have any thoughts or feedback.
Feedback: Don't use hashtags in HN comments, it comes across as tone-deaf and ignorant.
More precisely: Understand the kind of discourse expected on the platform you're using to communicate on, and only deviate from that if you've got a good reason to.
We wrote this blog for anyone who wants to take a quick peek at how AI/ML Engineering is shaping up and what some of the essential components of this new stack are.
It depends, while Yann Lecun has an interesting point of view.
The argument for explainability depends on the risk of harm from an AI model decision. Explaining why airplanes fly is moderately interesting but why did the 737-max crash is much more interesting and needed. While the former is probably only needed for people studying aerodynamics, the latter is meant for passengers, regulators, airlines, governments, etc.
Please let us know if you have any thoughts or feedback.