Print Email Facebook Twitter Active Monitoring of Neural Networks Title Active Monitoring of Neural Networks Author Lukina, A. (TU Delft Algorithmics) Schilling, Christian (Universität Konstanz) Henzinger, Thomas A. (Institute of Science and Technology (IST Austria)) Contributor Leiva, Edit Luis A. (editor) Pruski, Cédric (editor) Markovich, Réka (editor) Najjar, Amro (editor) Schommer, Christoph (editor) Date 2021 Abstract Neural-network classifiers are trained to achieve high prediction accuracy. However, their performance still suffers from frequently appearing inputs of unknown classes. As a component of a cyber-physical system, the classifier in this case can no longer be reliable and is typically retrained. We propose an algorithmic framework for monitoring reliability of a neural network. In contrast to static detection, a monitor wrapped in our framework operates in parallel with the classifier, communicates interpretable labeling queries to the human user, and incrementally adapts to their feedback. Subject monitoringneural networksnovelty detection To reference this document use: http://resolver.tudelft.nl/uuid:f468eb51-88f2-4f21-b928-b9516e93e946 Source BNAIC/BeneLearn 2021: 33rd Benelux Conference on Artificial Intelligence and 30th Belgian-Dutch Conference on Machine Learning Event 33rd Benelux Conference on Artificial Intelligence and30th Belgian-Dutch Conference on Machine Learning, 2021-11-10 → 2021-11-12, Esch-sur-Alzette, Luxembourg Part of collection Institutional Repository Document type conference paper Rights © 2021 A. Lukina, Christian Schilling, Thomas A. Henzinger Files PDF bnaic2021_preproceedings8.pdf 137.07 KB Close viewer /islandora/object/uuid:f468eb51-88f2-4f21-b928-b9516e93e946/datastream/OBJ/view