DEM: A Method for Certifying Deep Neural Network Classifier Outputs in Aerospace

arXiv:2401.02283v2 Announce Type: replace-cross
Abstract: Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software with deep neural network (DNN) components. Consequently, it is unclear how to allow aerospace systems to benefit from the deep learning revolution. Our work here seeks to address this challenge with a novel, output-centric approach for DNN certification. Our method employs statistical …

abstract aerospace apply arxiv classifier commercial components cs.lg cs.se deep neural network development dnn domain guidelines network neural network quality regulatory software software development standards type