Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- CNRS
- University of Antwerp
- Wageningen University & Research
- Amsterdam UMC
- Inria, the French national research institute for the digital sciences
- Maastricht University (UM)
- NTNU Norwegian University of Science and Technology
- Tilburg University
- University of Exeter
- University of Twente (UT)
- Aalborg Universitet
- Aalborg University
- Academic Europe
- Forschungszentrum Jülich
- Grenoble INP - Institute of Engineering
- Helmholtz-Zentrum Geesthacht
- KU LEUVEN
- Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V.
- Leipzig University •
- Luleå tekniska universitet
- Manchester Metropolitan University
- Monash University
- NOVA.id.FCT- Associação para a Inovação de Desenvolvimento da FCT
- NTNU - Norwegian University of Science and Technology
- Norwegian University of Life Sciences (NMBU)
- Politecnico di Milano
- Purdue University
- RMIT University
- SciLifeLab
- Tallinn University of Technology
- Technische Universität Dresden (TU Dresden)
- The University of Manchester
- Universidad de Alicante
- University of East Anglia
- University of Florida
- University of Groningen
- University of Texas at El Paso
- University of Warwick
- University of Warwick;
- 29 more »
- « less
-
Field
-
Inria, the French national research institute for the digital sciences | Montbonnot Saint Martin, Rhone Alpes | France | about 2 months ago
for representing knowledge graphs and OWL for formalising ontologies. In order to manage the heterogeneity of knowledge, alignments between ontologies make it possible to express the relationships between concepts
-
thesis in the field of continual graph learning. Continual graph learning studies how graph neural networks can learn from a sequence of evolving tasks, graphs, or distributions while retaining previously
-
generalized framework for extremal structural causal models on arbitrary directed acyclic graphs. Our new models will be able to incorporate non-standard extreme directions, which permits the modeling
-
unrealistic, and can therefore result in inadequate models. This project proposes a generalized framework for extremal structural causal models on arbitrary directed acyclic graphs. Our new models will be able
-
movement, gaze and interaction dynamics; encoding simulated cognition using graph- and transformer-based methods; training and evaluating models on publicly available and ethically collected clinical or sub
-
formulation. You will build machine learning models linking molecular structure (SMILES descriptors, fingerprints, graph representations) to reaction rate constants, connect molecular dynamics outputs
-
) Developing deep learning pipelines for multilayer segmentation and nanoscale transistor classification from microscopy images; (b) Designing graph-based inference models capable of reconstructing higher-level
-
, linear algebra, probability theory, (Bayesian) statistics, optimization and elementary graph theory Familiar with machine learning and deep learning Programming experience (Python or Julia) and their
-
, particularly Graph Neural Networks (GNNs), which show great promise. These methods have already demonstrated performance at least comparable to current Track Finding algorithms, with significant room for further
-
representation language. The thesis will particularly investigate approaches based on attributed graphs to model infrastructures, their topological relationships, inspection-derived observations, and the levels