dc.contributor.author | Neocleous, Costas K. | en |
dc.contributor.author | Schizas, Christos N. | en |
dc.contributor.editor | Madani K. | en |
dc.contributor.editor | Filipe J. | en |
dc.contributor.editor | Filipe J. | en |
dc.creator | Neocleous, Costas K. | en |
dc.creator | Schizas, Christos N. | en |
dc.date.accessioned | 2019-11-13T10:41:25Z | |
dc.date.available | 2019-11-13T10:41:25Z | |
dc.date.issued | 2014 | |
dc.identifier.isbn | 978-989-758-054-3 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/54591 | |
dc.description.abstract | 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. | en |
dc.publisher | INSTICC Press | en |
dc.source | NCTA 2014 - Proceedings of the International Conference on Neural Computation Theory and Applications | en |
dc.source | 6th International Conference on Neural Computation Theory and Applications, NCTA 2014, Part of the 6th International Joint Conference on Computational Intelligence, IJCCI 2014 | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84908884575&partnerID=40&md5=fa7128caaa056e9d6a22a3846f729abc | |
dc.subject | Neural networks | en |
dc.subject | Computation theory | en |
dc.subject | Pattern recognition | en |
dc.subject | Deep neural networks | en |
dc.subject | Adversarial examples | en |
dc.subject | Critical applications | en |
dc.subject | Deep learning | en |
dc.subject | Feature distribution | en |
dc.subject | Feature distribution in neural networks | en |
dc.title | On the claim for the existence of "Adversarial examples" in deep learning neural networks | en |
dc.type | info:eu-repo/semantics/conferenceObject | |
dc.description.startingpage | 306 | |
dc.description.endingpage | 309 | |
dc.author.faculty | 002 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Πληροφορικής / Department of Computer Science | |
dc.type.uhtype | Conference Object | en |
dc.description.notes | <p>Sponsors: Institute for Systems and Technologies of Information, Control and Communication (INSTICC) | en |
dc.description.notes | International Federation of Automatic Control (IFAC) | en |
dc.description.notes | Conference code: 114694</p> | en |
dc.contributor.orcid | Schizas, Christos N. [0000-0001-6548-4980] | |
dc.gnosis.orcid | 0000-0001-6548-4980 | |