Zobrazeno 1 - 10
of 4 238
pro vyhledávání: '"Böhle A"'
Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for classification. Such mod
Externí odkaz:
http://arxiv.org/abs/2407.14499
The validity of the subjective evaluation of steering feedback in driving simulators is crucial for modern vehicle development. Although there are established objective steering characteristics for the assessment of both stationary and dynamic feedba
Externí odkaz:
http://arxiv.org/abs/2403.17800
Technological advancements focus on developing comfortable and acceptable driving characteristics in autonomous vehicles. Present driving functions predominantly possess predefined parameters, and there is no universally accepted driving style for au
Externí odkaz:
http://arxiv.org/abs/2402.14432
Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they nonetheless
Externí odkaz:
http://arxiv.org/abs/2402.03119
Publikováno v:
Journal of Physics: Complexity, 5:025026, 2024
Synchronization is an essential collective phenomenon in networks of interacting oscillators. Twisted states are rotating wave solutions in ring networks where the oscillator phases wrap around the circle in a linear fashion. Here, we analyze Hopf bi
Externí odkaz:
http://arxiv.org/abs/2310.15698
Autor:
Oppotsch, Josephine, Böhle, Nadia, Held, Thomas, Fink, Mario, Fritsch, Miriam, Heinsius, Fritz-Herbert, Steinke, Matthias, Wiedner, Ulrich
Publikováno v:
Nuclear Instruments and Methods in Physics Research A 1057 (2023) 168767
Most detector systems used for positron emission particle tracking (PEPT) are very expensive due to the use of inorganic plastic scintillators combined with a high number of readout electronic channels. This work aims to reduce the overall cost of a
Externí odkaz:
http://arxiv.org/abs/2306.17429
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace the linear transformations in DNNs by our novel B-cos transformation. A
Externí odkaz:
http://arxiv.org/abs/2306.10898
Publikováno v:
Journal of Nonlinear Science, 34:77, 2024
Coupled oscillator networks provide mathematical models for interacting periodic processes. If the coupling is weak, phase reduction -- the reduction of the dynamics onto an invariant torus -- captures the emergence of collective dynamical phenomena,
Externí odkaz:
http://arxiv.org/abs/2305.04277
Most approaches for self-supervised learning (SSL) are optimised on curated balanced datasets, e.g. ImageNet, despite the fact that natural data usually exhibits long-tail distributions. In this paper, we analyse the behaviour of one of the most popu
Externí odkaz:
http://arxiv.org/abs/2303.13664
Publikováno v:
2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023, pp. 1922-1933
Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mitigate this, 'model guidance' has recently gained popularity, i.e. the
Externí odkaz:
http://arxiv.org/abs/2303.11932