Reachability for neural networks is NP-hard for single-hidden-layer networks with output dimension 1 and weights restricted to {-1,0,1}.
Reducibility Among Combinatorial Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CC 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reachability In Simple Neural Networks
Reachability for neural networks is NP-hard for single-hidden-layer networks with output dimension 1 and weights restricted to {-1,0,1}.