undefined | Better HN

0 pointselcapitan9y ago0 comments

Is there actually some way of formal verification of software that is driven mostly by machine learning? I imagine there's a small core of code that runs some trained models, but how are they being formally verified? How do we know there's not a blind spot in that model that turns out to be fatal under certain conditions?

0 comments

lallysingh9y ago

I'd imagine that you'd have some hybrid of ML and traditional code, and may be able to reason statistically about the ML sections, and user traditional (verified) code to cut the tail on the distribution.

All pipe dreams of mine, but the research potential here could be worth flaming truckloads of grant money :-)

j / k navigate · click thread line to collapse

0 pointselcapitan9y ago0 comments

0 comments

lallysingh9y ago

All pipe dreams of mine, but the research potential here could be worth flaming truckloads of grant money :-)

j / k navigate · click thread line to collapse