Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- DAAD
- ;
- Forschungszentrum Jülich
- Technical University of Munich
- University of Southern Denmark
- CWI
- Cranfield University
- Curtin University
- KINGS COLLEGE LONDON
- Maastricht University (UM)
- Nature Careers
- Radboud University
- University of Cambridge
- University of Groningen
- Vrije Universiteit Brussel
- ; University of Bristol
- Arts et Métiers Institute of Technology (ENSAM)
- Helmholtz-Zentrum Geesthacht
- Inria, the French national research institute for the digital sciences
- Institut Pasteur
- La Trobe University
- Maastricht University (UM); Maastricht
- Monash University
- SINTEF
- Simula Metropolitan Center for Digital Engineering
- Technical University of Denmark
- Technische Universität Berlin •
- The Max Planck Institute for Neurobiology of Behavior – caesar •
- UCT Prague
- Umeå University
- Umeå universitet
- University of Adelaide
- University of Amsterdam (UvA)
- University of Amsterdam (UvA); Amsterdam
- University of Antwerp
- University of California Irvine
- University of Göttingen •
- University of Nottingham
- University of Nottingham;
- University of Twente
- University of Tübingen
- Université Paris-Saclay GS Mathématiques
- Université libre de Bruxelles (ULB)
- Vrije Universiteit Brussel (VUB)
- 34 more »
- « less
-
Field
-
directions will be pursued to enhance column generation using machine learning. The first line of research focuses on improving scalability by using Graph Neural Networks to identify and eliminate non
-
of neural hydrology, where hydrological models are directly learned from data via machine learning (e.g., LSTM neural networks, [1]). Initially, these models ignored all physical background knowledge and did
-
machine learning frameworks such as recurrent neural networks and transformers. Models and datasets will be studied and benchmarked in key tasks relating to both prediction/forecasting and anomaly detection
-
neural networks and transformers. Models and datasets will be studied and benchmarked in key tasks relating to both prediction/forecasting and anomaly detection. Comparison with known analytic methods and
-
, artificial neural networks and bio-inspired robotics: "Rhythmic-reactive regulation for robotic locomotion" (Supervisor: Prof Fulvio Forni) will apply techniques from nonlinear control and optimisation
-
multi-electrode arrays to evaluate the activity of neural network formation Testing the inter-laboratory reproducibility of the model between the BfR, Berlin, and the TiHo, Hannover Preparation
-
to understand, predict, and treat diseases. You will work with multimodal biomedical datasets including omics, imaging, and patient data and apply cutting-edge AI models such as graph neural networks, transformer
-
research areas: Generative AI for Medical Imaging and Digital Biopsies Develop and interpret deep neural networks (DNNs) for automating non-destructive tissue-based analyses using high-parameter medical
-
operational employment. This doctoral research will thus leverage the power of graph neural networks – a novel ML architecture, capable of learning fundamental physical behaviour by modelling systems as graphs
-
algorithms. Graph Neural Networks. The candidate is expected to hold a relevant MSc degree in Computer Science, Data Science, Physics, (Applied) Mathematics, Computational Statistics or another field