Two new heuristic strategies are studied based on heuristics for the linear arrangement problem and a stochastic hill-climbing method for the two-sided bipartite crossing number problem. These are compared to the standard heuristic for two-sided bipartite drawing based on iteration of the barycentre method. Our experiments show that they can efficiently find good solutions.
The desire to provide robust guarantees on neural networks has never been more important, as their prevalence in society is increasing. One popular method that has seen a large amount of success is to use bounds on the activation functions within these networks to provide such guarantees. However, due to the large number of possible ways to bound the activation functions, there is a trade-off between conservativeness and complexity. We approach the problem from a different perspective, using polynomial optimisation and real algebraic geometry (the Positivstellensatz) to assert the emptiness of a semi-algebraic set. We show that by using the Positivstellensatz, bounds on the robustness guarantees can be tightened significantly over other popular methods, at the expense of computational resource. We demonstrate the effectiveness of this approach on networks that use the ReLU, sigmoid and tanh activation functions. This method can be extended to more activation functions, and combined with recent sparsityexploiting methods can result in a computationally acceptable method for verifying neural networks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.