1. Verification of Sigmoidal Artificial Neural Networks using iSAT
- Author
-
Grundt, Dominik, Jurj, Sorin Liviu, Hagemann, Willem, Kröger, Paul, and Fränzle, Martin
- Subjects
FOS: Computer and information sciences ,Computer Science - Symbolic Computation ,Computer Science - Machine Learning ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,nonlinear activation function ,Symbolic Computation (cs.SC) ,AI Verification ,Machine Learning (cs.LG) - Abstract
This paper presents an approach for verifying the behaviour of nonlinear Artificial Neural Networks (ANNs) found in cyber-physical safety-critical systems. We implement a dedicated interval constraint propagator for the sigmoid function into the SMT solver iSAT and compare this approach with a compositional approach encoding the sigmoid function by basic arithmetic features available in iSAT and an approximating approach. Our experimental results show that the dedicated and the compositional approach clearly outperform the approximating approach. Throughout all our benchmarks, the dedicated approach showed an equal or better performance compared to the compositional approach., In Proceedings SNR 2021, arXiv:2207.04391
- Published
- 2022
- Full Text
- View/download PDF