Search Results - "Hoedt, Katharina"

Constructing adversarial examples to investigate the plausibility of explanations in deep audio and image classifiers by Hoedt, Katharina, Praher, Verena, Flexer, Arthur, Widmer, Gerhard

“…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…”
Get full text

Defending a Music Recommender Against Hubness-Based Adversarial Attacks by Hoedt, Katharina, Flexer, Arthur, Widmer, Gerhard

“…Adversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence…”
Get full text

Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier by Foscarin, Francesco, Hoedt, Katharina, Praher, Verena, Flexer, Arthur, Widmer, Gerhard

“…Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially…”
Get full text