Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

Electronic Proceedings in Theoretical Computer Science, vol. 395, pp. 30–68

Abstract

In this paper, we extend an available neural network verification technique to support a wider class of piece-wise linear activation functions.Furthermore, we extend the algorithms, which provide in their original form exact respectively over-approximative results for bounded input sets represented as star sets, to allow also unbounded input sets.We implemented our algorithms and demonstrated their effectiveness in some case studies.

Authors 3

1. László Antal Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   RWTH Aachen University Aachen, Germany

2. Hana Masara Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   RWTH Aachen University Aachen, Germany

3. Erika Ábrahám Aachen

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University

   RWTH Aachen University Aachen, Germany