Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels
(Sprache: Englisch)
In this thesis, we study the robustness and generalization properties of Deep Neural Networks (DNNs) under various noisy regimes, due to corrupted inputs or labels. Such corruptions can be either random or intentionally crafted to disturb the target DNN....
Voraussichtlich lieferbar in 3 Tag(en)
versandkostenfrei
Buch (Kartoniert)
39.00 €
- Lastschrift, Kreditkarte, Paypal, Rechnung
- Kostenlose Rücksendung
Produktdetails
Produktinformationen zu „Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels “
Klappentext zu „Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels “
In this thesis, we study the robustness and generalization properties of Deep Neural Networks (DNNs) under various noisy regimes, due to corrupted inputs or labels. Such corruptions can be either random or intentionally crafted to disturb the target DNN. Inputs corrupted by maliciously designed perturbations are known as adversarial examples and have been shown to severely degrade the performance of DNNs. However, due to the non-linearity of DNNs, crafting such perturbations is non-trivial. [...]
Bibliographische Angaben
- Autor: Emilio Balda
- 2020, 134 Seiten, Maße: 14,8 x 21,1 cm, Kartoniert (TB), Englisch
- Verlag: Apprimus Verlag
- ISBN-10: 3863598024
- ISBN-13: 9783863598020
- Erscheinungsdatum: 14.01.2020
Sprache:
Englisch
Kommentar zu "Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels"
0 Gebrauchte Artikel zu „Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels“
Zustand | Preis | Porto | Zahlung | Verkäufer | Rating |
---|
Schreiben Sie einen Kommentar zu "Robustness Analysis of Deep Neural Networks in the Presence of Adversarial Perturbations and Noisy Labels".
Kommentar verfassen