Key points are not available for this paper at this time.
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers. We focus on sigmoid-based networks and exploit the fact that the sigmoid is the solution to a quadratic differential equation, which allows us to transform the neural network into an equivalent hybrid system. By composing the network's hybrid system with the plant's, we transform the problem into a hybrid system verification problem which can be solved using state-of-the-art reachability tools. We show that reachability is decidable for networks with one hidden layer and decidable for general networks if Schanuel's conjecture is true. We evaluate the applicability and scalability of Verisig in two case studies, one from reinforcement learning and one in which the neural network is used to approximate a model predictive controller.
Building similarity graph...
Analyzing shared references across papers
Loading...
Radoslav Ivanov
Rensselaer Polytechnic Institute
James Weimer
Vanderbilt University
Rajeev Alur
California University of Pennsylvania
California University of Pennsylvania
Building similarity graph...
Analyzing shared references across papers
Loading...
Ivanov et al. (Mon,) studied this question.
synapsesocial.com/papers/6a130986257f24f1de9eb921 — DOI: https://doi.org/10.1145/3302504.3311806
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: