Search Results for author: Mahmoud Elnaggar

Found 1 papers, 0 papers with code

ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers

no code implementations16 Jun 2020 James Ferlez, Mahmoud Elnaggar, Yasser Shoukry, Cody Fleming

In this paper, we consider the problem of creating a safe-by-design Rectified Linear Unit (ReLU) Neural Network (NN), which, when composed with an arbitrary control NN, makes the composition provably safe.

Cannot find the paper you are looking for? You can Submit a new open access paper.