Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/9768
Τίτλος: | On the claim for the existence of "Adversarial examples" in deep learning neural networks | Συγγραφείς: | Neocleous, Costas Schizas, Christos N. |
metadata.dc.contributor.other: | Νεοκλέους, Κώστας | Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Λέξεις-κλειδιά: | Adversarial examples;Deep neural networks;Feature distribution in neural networks | Ημερομηνία Έκδοσης: | Οκτ-2014 | Πηγή: | 6th International Conference on Neural Computation Theory and Applications, NCTA 2014, Part of the 6th International Joint Conference on Computational Intelligence, IJCCI 2014; Rome; Italy; 22 October 2014 through 24 October 2014 | Περίληψη: | A recent article in which it is claimed that adversarial examples exist in deep artificial neural networks (ANN) is critically examined. The newly discovered properties of ANNs are critically evaluated. Specifically, we point that adversarial examples can be serious problems in critical applications of pattern recognition. Also, they may stall the further development of artificial neural networks. We challenge the absolute existence of these examples, as this has not been universally proven yet. We also suggest that ANN structures, that correctly recognize adversarial examples, can be developed. | URI: | https://hdl.handle.net/20.500.14279/9768 | ISBN: | 978-989758054-3 | Rights: | © 2016 SCITEPRESS, Science and Technology Publications, Lda - All rights reserved. | Type: | Conference Papers | Affiliation: | Cyprus University of Technology University of Cyprus |
Publication Type: | Peer Reviewed |
Εμφανίζεται στις συλλογές: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
Page view(s) 20
406
Last Week
0
0
Last month
2
2
checked on 13 Οκτ 2024
Google ScholarTM
Check
Altmetric
Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα