@inproceedings{schwalbe2020_47274,
  title = {Strategies for Safety Goal Decomposition for Neural Networks},
  author = {Schwalbe, Gesina and Schels, Martin},
  year = {2020},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-47274},
  urn = {urn:nbn:de:bvb:473-irb-472744},
  url = {https://fis.uni-bamberg.de/handle/uniba/47274},
  language = {eng},
  abstract = {Neural networks (NNs) have become a key technology for solving highly complex tasks, and require integration into future safety argumentations. New safety relevant aspects introduced by NN based algorithms are: representativity of test cases, robustness, inner representation and logic, and failure detection for NNs. In this paper, a general argumentation structure for safety cases respecting these four aspects is proposed together with possible sources of evidence.},
  keywords = {neural network, safety argumentation, safety goal decomposition}
}
