Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Devos, Laurens"'
Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant research on designing approaches to
Externí odkaz:
http://arxiv.org/abs/2402.08586
Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a user's tr
Externí odkaz:
http://arxiv.org/abs/2206.13083
Machine learned models often must abide by certain requirements (e.g., fairness or legal). This has spurred interested in developing approaches that can provably verify whether a model satisfies certain properties. This paper introduces a generic alg
Externí odkaz:
http://arxiv.org/abs/2010.13880
Imagine being able to ask questions to a black box model such as "Which adversarial examples exist?", "Does a specific attribute have a disproportionate effect on the model's prediction?" or "What kind of predictions could possibly be made for a part
Externí odkaz:
http://arxiv.org/abs/2001.11905
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Davis, Jesse, Bransen, Lotte, Devos, Laurens, Meert, Wannes, Robberechts, Pieter, Van Haaren, Jan, Van Roy, Maaike
ispartof: pages:1-11 ispartof: AI Evaluation Beyond Metrics Workshop at IJCAI 2022 vol:3169 pages:1-11 ispartof: AI Evaluation Beyond Metrics Workshop location:Vienna, Austria date:22 Jul - 29 Jul 2022 status: Published online
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1131::b592535f137a9f980f6914eabea4d0f3
https://lirias.kuleuven.be/handle/20.500.12942/699507
https://lirias.kuleuven.be/handle/20.500.12942/699507
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Blockeel H; Department of Computer Science, KU Leuven, Leuven, Belgium.; Institute for Artificial Intelligence (Leuven.AI), KU Leuven, Leuven, Belgium., Devos L; Department of Computer Science, KU Leuven, Leuven, Belgium.; Institute for Artificial Intelligence (Leuven.AI), KU Leuven, Leuven, Belgium., Frénay B; Faculty of Computer Science, Université de Namur, Namur, Belgium., Nanfack G; Faculty of Computer Science, Université de Namur, Namur, Belgium., Nijssen S; ICTEAM, UCLouvain, Ottignies-Louvain-la-Neuve, Belgium.
Publikováno v:
Frontiers in artificial intelligence [Front Artif Intell] 2023 Jul 26; Vol. 6, pp. 1124553. Date of Electronic Publication: 2023 Jul 26 (Print Publication: 2023).
