14 citations · 44 across the 10 of their papers we have counts for
11 papers
Visual Transformers for Primates Classification and Covid Detection
Steffen Illium, Robert Müller, Andreas Sedlmeier +1
We apply the vision transformer, a deep machine learning model build around the attention mechanism, on mel-spectrogram representations of raw audio recordings. When adding mel-bas…
Capturing Dependencies within Machine Learning via a Formal Process Model
Fabian Ritz, Thomy Phan, Andreas Sedlmeier +7
The development of Machine Learning (ML) models is more than just a special case of software development (SD): ML models acquire properties and fulfill requirements even without di…
Quantifying Multimodality in World Models
Andreas Sedlmeier, Michael Kölle, Robert Müller +2
Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effect…
SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning
Fabian Ritz, Thomy Phan, Robert Müller +8
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they m…
Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms
Steffen Illium, Robert Müller, Andreas Sedlmeier +1
In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network en…
Policy Entropy for Out-of-Distribution Classification
Andreas Sedlmeier, Robert Müller, Steffen Illium +1
One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Su…