Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Robustness Verification for Classifier Ensembles

Autor: Gross, D., Jansen, N., Pérez, G.A., Raaijmakers, S., Hung, D.V., Sokolsky, O.

Publikováno v: Automated Technology for Verification and Analysis ISBN: 9783030591519
ATVA
Hung, D.V.; Sokolsky, O. (ed.), Automated Technology for Verification and Analysis: 18th International Symposium, ATVA 2020, Hanoi, Vietnam, October 19–23, 2020, Proceedings, 271-287. Cham : Springer International Publishing
STARTPAGE=271;ENDPAGE=287;ISSN=0302-9743;TITLE=Hung, D.V.; Sokolsky, O. (ed.), Automated Technology for Verification and Analysis: 18th International Symposium, ATVA 2020, Hanoi, Vietnam, October 19–23, 2020, Proceedings
Hung, D.V.; Sokolsky, O. (ed.), Automated Technology for Verification and Analysis: 18th International Symposium, ATVA 2020, Hanoi, Vietnam, October 19–23, 2020, Proceedings, pp. 271-287
Lecture notes in computer science

We give a formal verification procedure that decides whether a classifier ensemble is robust against arbitrary randomized attacks. Such attacks consist of a set of deterministic attacks and a distribution over this set. The robustness-checking proble

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eee66a3999bc32938af27ff292a02a59
https://doi.org/10.1007/978-3-030-59152-6_15

Hybrid ai: white paper

Autor: Meyer-Vitali, A.P., Bakker, R.M., Bekkum, M.A. van, Boer, M. de, Burghouts, G., Diggelen, J. van, Dijk, J., Grappiolo, C., Greeff, J. de, Huizing, A., Raaijmakers, S.

Hybrid Artificial Intelligence combines the best of two worlds: the power of recent advances in deep learning with the possibility to explicitly model human knowledge in connected systems. Together, this new generation of AI becomes more controllable

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::555390e78e06245c18fe97169a4994f1
http://resolver.tudelft.nl/uuid:510e0747-30f4-4af4-9447-9330b7bd4b47

Automatic analysis of online image data for law enforcement agencies by concept detection and instance search

Autor: Boer, M.H.T. de, Bouma, H., Kruithof, M.C., Haar, F.B. ter, Fischer, N.M., Hagendoorn, L.K., Joosten, B., Raaijmakers, S.

Publikováno v: Proc. SPIE, Vol. 10441, (2017)

The information available on-line and off-line, from open as well as from private sources, is growing at an exponential rate and places an increasing demand on the limited resources of Law Enforcement Agencies (LEAs). The absence of appropriate tools

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::cc68fb61f503795be04466ca6a8533f8
http://resolver.tudelft.nl/uuid:5a83ddd3-6fb7-48f7-93f2-92fa68cc3889

Thinking Aloud While Solving a Stock-Flow Task: Surfacing the Correlation Heuristic and Other Reasoning Patterns

Autor: Korzilius, H.P.L.M., Raaijmakers, S., Rouwette, E.A.J.A., Vennix, J.A.M.

Publikováno v: Systems Research and Behavioral Science, 31, 2, pp. 268-279
Systems Research and Behavioral Science, 31, 268-279

Contains fulltext : 116890.pdf (Publisher’s version ) (Closed access) In the literature, it is assumed that individuals, while performing stock-flow tasks, often use a correlation heuristic, a form of pattern matching in which they think that the b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1c7c0c54f500cbdb39e5c694f92e0d61
https://hdl.handle.net/2066/116890