Related Projects
Learning Temporal and Spectral Patterns from EEG Spectrograms using Deep Learning
Understanding the neural mechanisms underlying language production remains a central challenge in neuroscience. In ...
Engineering Sciences-
Continual Learning for very Short-Term Load Forecasting: A Case Study on Parts Cleaning
Industrial production systems play a central role in transition toward more flexible and sustainable energy use. In ...
Ingenieurwissenschaften -
Continual Learning for very Short-Term Load Forecasting: A Case Study on Parts Cleaning
Industrial production systems play a central role in transition toward more flexible and sustainable energy use. In ...
Engineering Sciences 
Feature Engineering for Deep Spatiotemporal Prediction in Last-Mile Logistics
Accurately predicting recipient presence at their delivery address is a critical challenge in last-mile logistics, as ...
Engineering SciencesElectrical Engineering and Information Technology-
mRNA Sequence Optimization via Neural Surrogate Modeling of Translation Initiation
In this Bachelor's thesis, a neural surrogate model was developed to predict the Minimum Free Energy (MFE) of mRNA ...
IngenieurwissenschaftenElektrotechnik und Informationstechnik -
mRNA Sequence Optimization via Neural Surrogate Modeling of Translation Initiation
In this Bachelor's thesis, a neural surrogate model was developed to predict the Minimum Free Energy (MFE) of mRNA ...
Engineering SciencesElectrical Engineering and Information Technology -
Physics Meets Peace Research: Nuclear Verification with HPC
In this peace research project, techniques for verifying the disarmament and arms control of nuclear weapons are ...
Natural SciencesParticles, Nuclei and Fields -
Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning
Contact-rich manipulation remains one of the most challenging tasks in robotics, requiring precise control under noisy ...
Ingenieurwissenschaften -
Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning
Contact-rich manipulation remains one of the most challenging tasks in robotics, requiring precise control under noisy ...
Engineering Sciences 
TEM Diffraction Pattern Analysis with Deep Learning Networks
The microstructure of a material strongly influences its properties and must therefore be studied carefully to tailor ...
IngenieurwissenschaftenMaterialwissenschaft-
TEM Diffraction Pattern Analysis with Deep Learning Networks
The microstructure of a material strongly influences its properties and must therefore be studied carefully to tailor ...
Engineering SciencesMaterials Science -
Training Neural Networks for Collision Avoidance
The increased popularity of drones and unmanned aerial vehicles (UAVs) for both commercial and recreational purposes has ...
Engineering Sciences -
Training Neural Networks for Collision Avoidance
The increased popularity of drones and unmanned aerial vehicles (UAVs) for both commercial and recreational purposes has ...
Ingenieurwissenschaften 
Training of Deep Learning Models for Water Segmentation
Floods represent one of the most frequent and damaging natural disasters, causing loss of life, infrastructure failure ...
Natural SciencesGeophysics and GeodesyEngineering SciencesComputer Science-
Universal Adversarial Perturbations: A Review
Machine learning has become an integral part of our society. In particular, the advancements driven by neural networks ...
IngenieurwissenschaftenInformatik -
Universal Adversarial Perturbations: A Review
Machine learning has become an integral part of our society. In particular, the advancements driven by neural networks ...
Engineering SciencesComputer Science 
End-to-end Learning for Multi-Embodiement Locomotion
The rapid development of robotics has enabled legged robots capable of performing highly dynamic tasks such as walking ...
Engineering SciencesComputer Science-
Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis
Up-to-date contact-rich manipulation tasks remain one of the grand challenges of robotics. Equipping robots with a sense ...
IngenieurwissenschaftenInformatik -
Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis
Up-to-date contact-rich manipulation tasks remain one of the grand challenges of robotics. Equipping robots with a sense ...
Engineering SciencesComputer Science 
Machine Learning Application in Automotive Catalysts
The computational resources of the Lichtenberg HPC were used in this project to train physics informed machine learning ...
Natural SciencesChemical Solid State and Surface Research
Major-Minor Mean Field Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) remains difficult to scale to many agents. Recent MARL using Mean Field ...
Engineering SciencesComputer Science
Parallel Finite Element Methods for Complex Flows of Complex Fluids
The objective of this ongoing project is the continuous development and advancement of effective simulation methods for ...
Engineering SciencesHeat Energy Technology, Thermal Machines, Fluid Mechanics
Parameter-Efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning
General-purpose intelligent robots are expected to simultaneously handle multiple tasks while interpreting various ...
Engineering SciencesComputer Science
SpyFi: Deep Learning for CSI-based Keylogging Side Channel Attacks
During keyboard typing, hand and finger movements induce alterations in Wi-Fi signal propagation, reflected in Channel ...
Engineering SciencesComputer Science-
Transkribus Model Training
Recognition of large amounts of printed or handwritten texts with to a high degree of accuracy – i. e. less than 0.1% ...
-
Transkribus Model Training
Recognition of large amounts of printed or handwritten texts with to a high degree of accuracy – i. e. less than 0.1% ...
Improving the Understanding of Neuromuscular Gait Control using Deep Reinforcement Learning
Understanding the underlying reward mechanisms of human locomotion and transferring this knowledge to humanoid robots is ...
Engineering SciencesComputer Science
CYWARN – Entwicklung von Strategien und Technologien zur Analyse und Kommunikation der Sicherheitslage im Cyberraum II
The increase in complex cyber-attacks illustrates the vulnerability of society and information infrastructure. In ...
Engineering SciencesComputer Science
Deep Implicit Collision Probability Fields
In robotic applications such as autonomous driving and whole-body control, ensuring safety is of utmost importance ...
Engineering SciencesComputer Science
Deep Reinforcement Learning for Robotics
Robotics platforms can massively benefit from novel Deep Reinforcement Learning approaches. However, robotics have ...
Engineering SciencesComputer Science
