Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Sinz, Fabian H."'
Understanding how the brain processes dynamic natural stimuli remains a fundamental challenge in neuroscience. Current dynamic neural encoding models either take stimuli as input but ignore shared variability in neural responses, or they model this v
Externí odkaz:
http://arxiv.org/abs/2410.16136
Autor:
Turishcheva, Polina, Fahey, Paul G., Vystrčilová, Michaela, Hansel, Laura, Froebe, Rachel, Ponder, Kayla, Qiu, Yongrong, Willeke, Konstantin F., Bashiri, Mohammad, Baikulov, Ruslan, Zhu, Yu, Ma, Lei, Yu, Shan, Huang, Tiejun, Li, Bryan M., De Wulf, Wolf, Kudryashova, Nina, Hennig, Matthias H., Rochefort, Nathalie L., Onken, Arno, Wang, Eric, Ding, Zhiwei, Tolias, Andreas S., Sinz, Fabian H., Ecker, Alexander S
Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive mode
Externí odkaz:
http://arxiv.org/abs/2407.09100
Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly combined
Externí odkaz:
http://arxiv.org/abs/2406.12625
Single camera 3D pose estimation is an ill-defined problem due to inherent ambiguities from depth, occlusion or keypoint noise. Multi-hypothesis pose estimation accounts for this uncertainty by providing multiple 3D poses consistent with the 2D measu
Externí odkaz:
http://arxiv.org/abs/2403.06164
Autor:
Turishcheva, Polina, Fahey, Paul G., Hansel, Laura, Froebe, Rachel, Ponder, Kayla, Vystrčilová, Michaela, Willeke, Konstantin F., Bashiri, Mohammad, Wang, Eric, Ding, Zhiwei, Tolias, Andreas S., Sinz, Fabian H., Ecker, Alexander S.
Understanding how biological visual systems process information is challenging due to the complex nonlinear relationship between neuronal responses and high-dimensional visual input. Artificial neural networks have already improved our understanding
Externí odkaz:
http://arxiv.org/abs/2305.19654
Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this method is unsu
Externí odkaz:
http://arxiv.org/abs/2305.14890
Due to depth ambiguities and occlusions, lifting 2D poses to 3D is a highly ill-posed problem. Well-calibrated distributions of possible poses can make these ambiguities explicit and preserve the resulting uncertainty for downstream tasks. This study
Externí odkaz:
http://arxiv.org/abs/2210.11179
Autor:
Willeke, Konstantin F., Fahey, Paul G., Bashiri, Mohammad, Pede, Laura, Burg, Max F., Blessing, Christoph, Cadena, Santiago A., Ding, Zhiwei, Lurz, Konstantin-Klemens, Ponder, Kayla, Muhammad, Taliah, Patel, Saumil S., Ecker, Alexander S., Tolias, Andreas S., Sinz, Fabian H.
The neural underpinning of the biological visual system is challenging to study experimentally, in particular as the neuronal activity becomes increasingly nonlinear with respect to visual input. Artificial neural networks (ANNs) can serve a variety
Externí odkaz:
http://arxiv.org/abs/2206.08666
Autor:
Safarani, Shahd, Nix, Arne, Willeke, Konstantin, Cadena, Santiago A., Restivo, Kelli, Denfield, George, Tolias, Andreas S., Sinz, Fabian H.
Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Re
Externí odkaz:
http://arxiv.org/abs/2107.14344
In recent years, artificial neural networks have achieved state-of-the-art performance for predicting the responses of neurons in the visual cortex to natural stimuli. However, they require a time consuming parameter optimization process for accurate
Externí odkaz:
http://arxiv.org/abs/2010.11810