Double Backpropagation with Applications to Robustness and Saliency Map Interpretability

Maaß, PeterEtmann, ChristianChristianEtmann2020-09-302020-09-302020-02-14https://media.suub.uni-bremen.de/handle/elib/450110.26092/elib/298This thesis is concerned with works in connection to double backpropagation, which is a phenomenon that arises when first-order optimization methods are applied to a neural network's loss function, if this contains derivatives. Its connection to robustness and saliency map interpretability is explained.eninfo:eu-repo/semantics/openAccessdeep learningneural networksartificial intelligencedouble backpropagationrobustnesssaliency mapinterpretabilitycomputer visionMALDImass spectrometrymachine learningdata sciencestatistics510Double Backpropagation with Applications to Robustness and Saliency Map InterpretabilityDoppelte Fehler-Rückpropagierung mit Anwendungen zu Robustheit und Interpretierbarkeit der SalienzkarteDissertationurn:nbn:de:gbv:46-00108645-13urn:nbn:de:gbv:46-elib45018