A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function
As the railway domain progresses towards autonomy, maintaining safety at levels
comparable to human-operated systems is a crucial challenge. Autonomous trains require …
comparable to human-operated systems is a crucial challenge. Autonomous trains require …
Fully Automatic Neural Network Reduction for Formal Verification
Formal verification of neural networks is essential before their deployment in safety-critical
applications. However, existing methods for formally verifying neural networks are not yet …
applications. However, existing methods for formally verifying neural networks are not yet …
Monitoring of Neural Network Classifiers using Neuron Activation Paths
F Boudardara, A Boussif, PJ Meyer… - … Conference on Verification …, 2024 - hal.science
To be deployed in safety critical applications, neural network (NN) systems require to be
verified during the development phase and then monitored during the runtime phase. The …
verified during the development phase and then monitored during the runtime phase. The …