Prof. Dr.

Wrobel, Stefan

Filters
Reset filters

Settings
Now showing 1 - 3 of 3
  • Publication
    Wasserstein Dropout
    ( 2022-09-08)
    Sicking, Joachim
    ;
    Akila, Maram
    ;
    Pintz, Maximilian Alexander
    ;
    Wirtz, Tim
    ;
    Wrobel, Stefan
    ;
    Fischer, Asja
    Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncertainties are often hybrid, combining parametric models with explicit or implicit (dropout-based) ensembling. We take another pathway and propose a novel approach to uncertainty quantification for regression tasks, Wasserstein dropout, that is purely non-parametric. Technically, it captures aleatoric uncertainty by means of dropout-based sub-network distributions. This is accomplished by a new objective which minimizes the Wasserstein distance between the label distribution and the model distribution. An extensive empirical analysis shows that Wasserstein dropout outperforms state-of-the-art methods, on vanilla test data as well as under distributional shift in terms of producing more accurate and stable uncertainty estimates.
  • Publication
    Vertrauenswürdiger Einsatz von Künstlicher Intelligenz
    (Fraunhofer IAIS, 2019)
    Cremers, Armin B.
    ;
    Englander, Alex
    ;
    Gabriel, Markus
    ;
    Hecker, Dirk
    ;
    Mock, Michael
    ;
    Poretschkin, Maximilian
    ;
    Rosenzweig, Julia
    ;
    Rostalski, Frauke
    ;
    Sicking, Joachim
    ;
    Volmer, Julia
    ;
    Voosholz, Jan
    ;
    Voß, Angelika
    ;
    Wrobel, Stefan
    Die vorliegende Publikation dient als Grundlage für die interdisziplinäre Entwicklung einer Zertifizierung von Künstlicher Intelligenz. Angesichts der rasanten Entwicklung von Künstlicher Intelligenz mit disruptiven und nachhaltigen Folgen für Wirtschaft, Gesellschaft und Alltagsleben verdeutlicht sie, dass sich die hieraus ergebenden Herausforderungen nur im interdisziplinären Dialog von Informatik, Rechtswissenschaften, Philosophie und Ethik bewältigen lassen. Als Ergebnis dieses interdisziplinären Austauschs definiert sie zudem sechs KI-spezifische Handlungsfelder für den vertrauensvollen Einsatz von Künstlicher Intelligenz: Sie umfassen Fairness, Transparenz, Autonomie und Kontrolle, Datenschutz sowie Sicherheit und Verlässlichkeit und adressieren dabei ethische und rechtliche Anforderungen. Letztere werden mit dem Ziel der Operationalisierbarkeit weiter konkretisiert.
  • Publication
    Effcient Decentralized Deep Learning by Dynamic Model Averaging
    ( 2019)
    Kamp, Michael
    ;
    Adilova, Linara
    ;
    Sicking, Joachim
    ;
    Hüger, Fabian
    ;
    Schlicht, Peter
    ;
    Wirtz, Tim
    ;
    Wrobel, Stefan
    We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared to periodically communicating state-of-the-art approaches. Moreover, we derive a communication bound that scales well with the hardness of the serialized learning problem. The reduction in communication comes at almost no cost, as the predictive performance remains virtually unchanged. Indeed, the proposed protocol retains loss bounds of periodically averaging schemes. An extensive empirical evaluation validates major improvement of the trade-off between model performance and communication which could be beneficial for numerous decentralized learning applications, such as autonomous driving, or voice recognition and image classification on mobile phones.