138 citations
- Daniel F. B. Haeufle3 · h 18
- Lisa M. Koch2 profiles2 · h 14
- Martin A. Giese2 profiles2 · h 4
- Pierre Schumacher2 · h 7
- Addison Salvador1 · h 0
- Adib Bazgir1 · h 10
- Aditya Raghavan1 · h 2
- Alexander Badri-Sprowitz1 · h 2
- Alexander Badri-Spröwitz1 · h 10
- Alexander J. Pattison1 · h 0
- Alexander Kiefer1 · h 2
- A. Maier1 · h 6
- University of TübingenDE7 papers
- Max Planck Institute for Intelligent SystemsDE4 papers
- University of StuttgartDE3 papers
- Aalto UniversityFI1 paper
- Applied Spectra (United States)US1 paper
- AREA Science ParkIT1 paper
- Argonne National LaboratoryUS1 paper
- Aspiring Scholars Directed Research ProgramUS1 paper
- Bayreuth Medical CenterDE1 paper
- Bernstein Center for Computational Neuroscience TübingenDE1 paper
- Centre de Recerca MatemàticaES1 paper
- Charles UniversityCZ1 paper
11 papers
Appearance-free Action Recognition: Zero-shot Generalization in Humans and a Two-Pathway Model
Prerana Kumar, Martin A. Giese
Action recognition is a fundamental ability for social species. Yet, its underlying computations are not well understood. Classical psychophysical studies using simplified stimuli…
Mic-hackathon 2024: Hackathon on Machine Learning for Electron and Scanning Probe Microscopy
Utkarsh Pratiush, Austin Houston, Kamyar Barakati +70
Microscopy is a primary source of information on materials structure and functionality at nanometer and atomic scales. The data generated is often well-structured, enriched with me…
Delving into LLM-assisted writing in biomedical publications through excess vocabulary
Dmitry Kobak, Rita González-Márquez, Emőke-Ágnes Horvát +1
Large language models (LLMs) like ChatGPT can generate and revise text with human-level performance. These models come with clear limitations: they can produce inaccurate informati…
Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
Susu Sun, Stefano Woerner, Andreas Maier +2
Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions…
Learning to Control Emulated Muscles in Real Robots: Towards Exploiting Bio-Inspired Actuator Morphology
Pierre Schumacher, Lorenz Krause, Jan Schneider +3
Recent studies have demonstrated the immense potential of exploiting muscle actuator morphology for natural and robust movement -- in simulation. A validation on real robotic hardw…
Disentangling representations of retinal images with generative models
Sarah Müller, Lisa M. Koch, Hendrik P. A. Lensch +1
Retinal fundus images play a crucial role in the early detection of eye diseases. However, the impact of technical factors on these images can pose challenges for reliable AI appli…