Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Landgraf, Tim"'
Recent advances in out-of-distribution (OOD) detection on image data show that pre-trained neural network classifiers can separate in-distribution (ID) from OOD data well, leveraging the class-discriminative ability of the model itself. Methods have
Externí odkaz:
http://arxiv.org/abs/2405.17164
Many European citizens become targets of the Kremlin propaganda campaigns, aiming to minimise public support for Ukraine, foster a climate of mistrust and disunity, and shape elections (Meister, 2022). To address this challenge, we developed ''Check
Externí odkaz:
http://arxiv.org/abs/2401.15717
Autor:
Solopova, Veronika, Gruszczynski, Adrian, Rostom, Eiad, Cremer, Fritz, Witte, Sascha, Zhang, Chengming, Plößl, Fernando Ramos López Lea, Hofmann, Florian, Romeike, Ralf, Gläser-Zikuda, Michaela, Benzmüller, Christoph, Landgraf, Tim
Written reflective practice is a regular exercise pre-service teachers perform during their higher education. Usually, their lecturers are expected to provide individual feedback, which can be a challenging task to perform on a regular basis. In this
Externí odkaz:
http://arxiv.org/abs/2307.07523
The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narratives. These polarized campaigns have led to mutual accusations of mis
Externí odkaz:
http://arxiv.org/abs/2301.10604
Autor:
Sixt, Leon, Landgraf, Tim
Saliency methods attempt to explain deep neural networks by highlighting the most salient features of a sample. Some widely used methods are based on a theoretical framework called Deep Taylor Decomposition (DTD), which formalizes the recursive appli
Externí odkaz:
http://arxiv.org/abs/2211.08425
K-nearest neighbors (KNN) is one of the earliest and most established algorithms in machine learning. For regression tasks, KNN averages the targets within a neighborhood which poses a number of challenges: the neighborhood definition is crucial for
Externí odkaz:
http://arxiv.org/abs/2205.08434
A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respective predictions remains unclear. We conducted a user study (N=240) to te
Externí odkaz:
http://arxiv.org/abs/2204.11642
Autor:
Klamser, Pascal P., Gómez-Nava, Luis, Landgraf, Tim, Jolles, Jolle W., Bierbach, David, Romanczuk, Pawel
A variety of agent-based models has been proposed to account for the emergence of coordinated collective behavior of animal groups from simple interaction rules. A common, simplifying assumption of such collective movement models, is the consideratio
Externí odkaz:
http://arxiv.org/abs/2106.00959
Autor:
Landgraf, Tim, Moenck, Hauke J., Gebhardt, Gregor H. W., Weimar, Nils, Hocke, Mathis, Maxeiner, Moritz, Musiolek, Lea, Krause, Jens, Bierbach, David
Collective motion is commonly modeled with simple interaction rules between agents. Yet in nature, numerous observables vary within and between individuals and it remains largely unknown how animals respond to this variability, and how much of it may
Externí odkaz:
http://arxiv.org/abs/2009.06633
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In th
Externí odkaz:
http://arxiv.org/abs/2001.00396