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

SAT solvers are really fast now. Some sort of "neural SAT problem definition" followed by solving it seems to be an interesting direction, but I'm relatively naive on it all. Not sure how training would work since there's no backprop through Boolean logic.




Differentiable SAT solvers is a thing.


Pointers please; not just off-hand mentions leaving others to scratch their heads about what you mean! :-)




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: