Leveraging Satisfiability Modulo Theory Solvers for Verification of Neural Networks in Predictive Maintenance Applications

Interest in machine learning and neural networks has increased significantly recent years. However, their applications are limited safety-critical domains due to the lack of formal guarantees on reliability behavior. This paper shows advances satisfiability modulo theory solvers used context verification with piece-wise linear transcendental activation functions. An experimental analysis is conducted using trained a real-world predictive maintenance dataset. study contributes research enhancing safety through verification, enabling deployment domains.