@article{Far2021, Author = {Farzaneh Moradkhani, Martin Fränzle}, Title = {Functional verification of cyber-physical systems containing machine-learnt components}, Year = {2021}, Pages = {277-287}, Month = {11}, Booktitle = {it-Information Technology (63), De Gruyter Oldenbourg, issue: 5-6}, type = {article}, Abstract = {Functional architectures of cyber-physical systems increasingly comprise components that are generated by training and machine learning rather than by more traditional engineering approaches, as necessary in safety-critical application domains, poses various unsolved challenges. Commonly used computational structures underlying machine learning, like deep neural networks, still lack scalable automatic verification support. Due to size, non-linearity, and non-convexity, neural network verification is a challenge to state-of-art Mixed Integer linear programming (MILP) solvers and satisfiability modulo theories (SMT) solvers , . In this research, we focus on artificial neural network with activation functions beyond the Rectified Linear Unit (ReLU). We are thus leaving the area of piecewise linear function supported by the majority of SMT solvers and specialized solvers for Artificial Neural Networks (ANNs), the …} } @COMMENT{Bibtex file generated on }