no code implementations • 26 Aug 2022 • Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer
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.
1 code implementation • 24 May 2022 • Katharina Hoedt, Arthur Flexer, Gerhard Widmer
Adversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence mechanisms.
1 code implementation • 19 Jul 2021 • Verena Praher, Katharina Prinz, Arthur Flexer, Gerhard Widmer
The basic idea is to identify a small set of human-understandable features of the classified example that are most influential on the classifier's prediction.
no code implementations • 14 Aug 2020 • Katharina Prinz, Arthur Flexer, Gerhard Widmer
We explore how much can be learned from noisy labels in audio music tagging.
no code implementations • 29 Jul 2020 • Katharina Prinz, Arthur Flexer
Small adversarial perturbations of input data are able to drastically change performance of machine learning systems, thereby challenging the validity of such systems.
1 code implementation • 2 Dec 2019 • Roman Feldbauer, Thomas Rattei, Arthur Flexer
Users will find all functionality of the scikit-learn neighbors package, plus additional support for transparent hubness reduction and approximate nearest neighbor search.
no code implementations • 7 Sep 2017 • Monika Doerfler, Thomas Grill, Roswitha Bammer, Arthur Flexer
The theoretical results show that approximately reproducing mel-spectrogram coefficients by applying adaptive filters and subsequent time-averaging is in principle possible.