A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks — mentioned by huyegn

Thu, 06 Feb 2020 06:15:22 GMT

I stated that rather than explainability, for most use cases, people just want calibrated and robust uncertainty estimates NOT low quality and uncalibrated uncertainties estimates. Your example points to models that provide low quality uncertainty estimates, but that's not true for all deep learning models. I believe it's these low quality uncertainty estimates that lead people to look toward "explainability" as a solution, but for the majority of use cases, I think people just want better uncertainty estimates so that they can "know when they're model doesn't know". There are techniques now…

Paper and discussion history. A mention is not an endorsement.

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks · HackerPapers discussions

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks — mentioned by huyegn