708 citations · 727 across the 2 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2018
Learning a SAT Solver from Single-Bit Supervision
Daniel Selsam, Matthew Lamm, Benedikt Bünz +3
We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not compe…
cs.AI2017★ 19 cited
Graph Neural Networks and Boolean Satisfiability
Benedikt Bünz, Matthew Lamm
In this paper we explore whether or not deep neural architectures can learn to classify Boolean satisfiability (SAT). We devote considerable time to discussing the theoretical prop…