News for hackers. Stuff that matters.

A comment on The Mythos of Model Interpretability in Machine Learning. Parent comment

Re:The Mythos of Model Interpretability in Machine Learning by lasso1 on Thursday July 19, 2018 @06:14AM (#17565041)
Along the same lines, convergence is mentioned as a candidate for interpretability but convexity is not mentioned even once.
[ Parent | on HN ]
Re:The Mythos of Model Interpretability in Machine Learning by danielmorozoff on Thursday July 19, 2018 @09:00AM (#17565778)
This is a very interesting notion, could you elaborate why convexity would be a candidate? Convexity defining a class is clear, but as a proxy for interpretability I have not heard this before. I would assume this would need some measure of degree of convexity - different than strong > strict > convex
[ Parent | on HN ]