9 citations
- Ruhr University BochumDE6 papers
- Belarusian State UniversityBY2 papers
- Beckman Laser Institute and Medical ClinicUS1 paper
- College of Staten IslandUS1 paper
- Courant Institute of Mathematical SciencesUS1 paper
- Eftas Remote Sensing Technology Transfer (Germany)DE1 paper
- Fraunhofer Institute for Microelectronic Circuits and SystemsDE1 paper
- Ghent UniversityBE1 paper
- Heidelberg UniversityDE1 paper
- Hochschule für Gesundheit - University of Applied SciencesDE1 paper
- Indian Institute of Science BangaloreIN1 paper
- Institute of Space Science - INFLPR SubsidiaryRO1 paper
14 papers
Multiple Additive Neural Networks for Structured and Unstructured Data
Janis Mohr, Jörg Frochte
This paper extends and explains the Multiple Additive Neural Networks (MANN) methodology, an enhancement to the traditional Gradient Boosting framework, utilizing nearly shallow ne…
Organizational Practices and Socio-Technical Design of Human-Centered AI
Thomas Herrmann
This contribution explores how the integration of Artificial Intelligence (AI) into organizational practices can be effectively framed through a socio-technical perspective to comp…
One-Shot Identification with Different Neural Network Approaches
Janis Mohr, Jörg Frochte
Convolutional neural networks (CNNs) have been widely used in the computer vision community, significantly improving the state-of-the-art. But learning good features often is compu…
Exploring Student Expectations and Confidence in Learning Analytics
Hayk Asatryan, Basile Tousside, Janis Mohr +5
Learning Analytics (LA) is nowadays ubiquitous in many educational systems, providing the ability to collect and analyze student data in order to understand and optimize learning a…
Group and Exclusive Sparse Regularization-based Continual Learning of CNNs
Basile Tousside, Janis Mohr, Jörg Frochte
We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic f…
Synthetic Turbulence via an Instanton Gas Approximation
Timo Schorlepp, Katharina Kormann, Jeremiah Lübke +2
Sampling synthetic turbulent fields as a computationally tractable surrogate for direct numerical simulations (DNS) is an important practical problem in various applications, and a…