Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Hoedt, Katharina"'
Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can
Externí odkaz:
http://arxiv.org/abs/2208.12485
Adversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence mechanisms. We present a new line of defence against attacks which exploit a vulnerability of rec
Externí odkaz:
http://arxiv.org/abs/2205.12032
Autor:
Hoedt, Katharina1 (AUTHOR) katharina.hoedt@jku.at, Praher, Verena1 (AUTHOR) verena.praher@jku.at, Flexer, Arthur1 (AUTHOR), Widmer, Gerhard1,2 (AUTHOR)
Publikováno v:
Neural Computing & Applications. May2023, Vol. 35 Issue 14, p10011-10029. 19p.
Given the rise of deep learning and its inherent black-box nature, the desire to interpret these systems and explain their behaviour became increasingly more prominent. The main idea of so-called explainers is to identify which features of particular
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3361::259f33e9cdd2e90c91e4212498eba3e2
https://epub.jku.at/doi/10.1007/s00521-022-07918-7
https://epub.jku.at/doi/10.1007/s00521-022-07918-7
Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85f6718bfee0d867a21eb1c341834166
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.