Projekte
Hessische Wissenschaftlerinnen und Wissenschaftler unterschiedlichster Disziplinen benötigen Hochleistungsrechnen für ihre Forschung.
Projekte
Kategorie
Jahr
Software
Universität
Cluster
Projekte
Displaying 31 - 51 of 51
CYWARN – Entwicklung von Strategien und Technologien zur Analyse und Kommunikation der Sicherheitslage im Cyberraum
The increase in complex cyber-attacks illustrates the vulnerability of society and information infrastructure. In ...
IngenieurwissenschaftenInformatik
Learning for Decentralized, Long-Horizon Manipulation
Achieving long-horizon dexterous manipulation remains a challenging problem in robotics. There exists a long history of ...
IngenieurwissenschaftenSystemtechnik-
Visuomotor Control of Pouring Liquids
Natural visuomotor control tasks such as pouring liquids into cups are trivial for humans but are challenging to model ...
LebenswissenschaftenNeurowissenschaft 
Algorithm Unfolding in Multicell Downlink MIMO Precoding
In wireless communications, beamforming is utilized for the reception and transmission of directional wireless signals ...
IngenieurwissenschaftenElektrotechnik und Informationstechnik
Bayesian Inference of Cyclic Transcription Dynamics
Transcription is the process of converting DNA into RNA and is essential to cellular life. The transcription process ...
NaturwissenschaftenStatistische Physik, Weiche Materie, Biologische Physik, Nichtlineare Dynamik
Deep Reinforcement Learning: Benchmarking, Algorithms and Applications
Deep Learning is the major component of the success of most new Artificial Intelligence applications. A new promising ...
Ingenieurwissenschaften
Designing an Efficient Neural Architecture Search
Within the last decade, deep neural networks have attracted much attention from academia and industry. Such a wide ...
IngenieurwissenschaftenInformatik
Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System
Normative computational models of human sensorimotor behavior based on optimal feedback control with signal-dependent ...
LebenswissenschaftenNeurowissenschaft
Learning Physically Interactive Behaviours for Human-Robot Interaction
Modeling interaction dynamics to generate robot trajectories that enable a robot to adapt and react to a human’s actions ...
IngenieurwissenschaftenInformatik
Measure-Valued Derivatives for Reinforcement Learning
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy ...
IngenieurwissenschaftenInformatik-
Noise Resilient Empirical Performance Modeling with Deep Neural Networks
Empirical performance modeling is a proven instrument to analyze the scaling behavior of HPC applications. Using a set ...
IngenieurwissenschaftenInformatik 
When to Trust Your Model in Model-based Value Expansion?
Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the ...
IngenieurwissenschaftenInformatik
Balloon Estimators for Improving and Scaling the Nonparametric Off-Policy Policy Gradient
The Nonparametric Off-Policy Policy Gradient (NOPG) is a policy gradient algorithm to solve reinforcement learning tasks ...
IngenieurwissenschaftenInformatik-
Constraint Space Projection Reinforcement Learning
The aim of the project is to develop a new family of optimization algorithms to handle convex constraints and evaluate ...
IngenieurwissenschaftenInformatik -
Evaluating and Improving Recurrent Kalman Networks
Precise models of the system dynamics are crucial for model-based control and reinforcement learning (RL) in autonomous ...
IngenieurwissenschaftenInformatik 
Interpretable Reinforcement Learning
Deep Reinforcement Learning can solve difficult high dimensional tasks, by exploiting the expressive representation ...
Engineering SciencesComputer Science-
Model Learning With Recurrent Kalman Networks
Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system ...
IngenieurwissenschaftenInformatik 
Network Traffic Prediction with Neural Networks
The bursty nature of network traffic is one of the main reasons for congestion in data centers, since traffic loads are ...
IngenieurwissenschaftenInformatik-
Performance Modeling at a Discount
Identifying scalability bugs in parallel applications is a vital but also laborious and expensive task. Empirical ...
IngenieurwissenschaftenInformatik -
Stochastic Search for Applications in Robotics
Stochastic-search algorithms are problem independent algorithms well-suited for black-box optimization of an objective ...
IngenieurwissenschaftenInformatik -
Efficient representations of deep neural networks
Deep neural networks (DNNs) have gained extreme popularity in recent years, advancing state-of-the- art results in ...
IngenieurwissenschaftenInformatik
