Building Trust in the Black Box: An Introduction to AI Explainability

In recent years, the themes of transparency and trust have become increasingly central to the way that humans develop, manage, regulate, and monitor ML technologies. It is clear that now more than ever stakeholders need tools to detect model bias and understand model behavior. At Fiddler Labs, we're building a general-purpose Explainable AI Engine to solve these problems at scale.

In this talk, I will introduce the core ideas behind explainable AI and cover the cutting edge of modern explainability technology that we are harnessing into our core product at Fiddler.

Speaker; Luke Merrick, Magnimind