978 citations
- University of CopenhagenDK77 papers
- Technical University of DenmarkDK18 papers
- Institute for Scientific InterchangeIT17 papers
- Complexity Science HubAT16 papers
- Institut national de recherche en sciences et technologies du numériqueFR13 papers
- University College CopenhagenDK12 papers
- University of OxfordGB12 papers
- Aarhus UniversityDK11 papers
- Aalborg UniversityDK10 papers
- Chalmers University of TechnologySE10 papers
- ETH ZurichCH9 papers
- Google (United States)US9 papers
29 papers · 1 filter
Exploring Deep Learning Models for EEG Neural Decoding
Laurits Dixen, Stefan Heinrich, Paolo Burelli
Neural decoding is an important method in cognitive neuroscience that aims to decode brain representations from recorded neural activity using a multivariate machine learning model…
TensorSocket: Shared Data Loading for Deep Learning Training
Ties Robroek, Neil Kim Nielsen, Pınar Tözün
Training deep learning models is a repetitive and resource-intensive process. Data scientists often train several models before landing on a set of parameters (e.g., hyper-paramete…
Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning
Ralf Raumanns, Gerard Schouten, Josien P. W. Pluim +1
The influence of bias in datasets on the fairness of model predictions is a topic of ongoing research in various fields. We evaluate the performance of skin lesion classification u…
Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies
Finn Rietz, Erik Schaffernicht, Stefan Heinrich +1
Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both…
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
Martin Gubri, Dennis Ulmer, Hwaran Lee +2
Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial,…
Modyn: Data-Centric Machine Learning Pipeline Orchestration
Maximilian Böther, Ties Robroek, Viktor Gsteiger +4
In real-world machine learning (ML) pipelines, datasets are continuously growing. Models must incorporate this new training data to improve generalization and adapt to potential di…