AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Importance of Explainability in AI
I've been on the record before as being somewhat of an explainability skeptic. We wrote a paper trying to lay out why we think that explainability for AI is not a good trust mechanism. One of the biggest limitations in AI and health care is going to be the sparsity of data. But if you have biomarkers, these are priors. Why not use them?