2 papers
cs.LO2026
Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks
Tomáš Kolárik, Faezeh Labbaf, Fabrizio Leopardi +3
Formal explainability of classifying neural networks (NNs) is an active area of research, providing explanations with provable guarantees of the classification within continuous re…
eess.SY2022
Railway Scheduling Using Boolean Satisfiability Modulo Simulations
Tomáš Kolárik, Stefan Ratschan
Railway scheduling is a problem that exhibits both non-trivial discrete and continuous behavior. In this paper, we simulate train networks at a low level, where a number of timing…