The purpose of post-prediction explanations would be to increase confidence of a... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

		Narhem 6 days ago \| parent \| context \| favorite \| on: Kolmogorov-Arnold networks may make neural network... The purpose of post-prediction explanations would be to increase confidence of a practitioner to use said inference. It’s a disconnect between finding a real life “AI” and trying to find something which works and you can have a form of trust with.

solidninja 5 days ago [–]

Is there a study of "smooth"/"stable" "AI" algorithms - i.e. if you feed them input that is "close" then then the output is also "close"? (smooth as in smoothly differentiable/stable as in stable sorted)

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