>> Interpretability obviously doesn't hurt accuracy. Why do you say this? From w... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		1_over_n on Jan 4, 2020 \| parent \| context \| favorite \| on: Why are we using black box models in AI when we do... >> Interpretability obviously doesn't hurt accuracy. Why do you say this? From what i have seen it certainly can and does. For some industries finding a trade off where the magic is. https://link.springer.com/article/10.1007/s10664-018-9638-1 https://www.oreilly.com/ideas/predictive-modeling-striking-a...

dchichkov on Jan 5, 2020 [–]

You can take nearly any black box model and add some interpretability into it, without modifying this model. No modifications to the model, so accuracy stays the same.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact