Sort by
Refine Your Search
-
Vacancies 2x PhD positions in the Mathematical Foundations of Machine Learning on Graphs and Networks Key takeaways The Discrete Mathematics and Mathematical Programming (DMMP) group
-
on Graphs: Symmetry Meets Structure (LOGSMS). The field of Machine Learning on Graphs aims to extract knowledge from graph-structured and network data through powerful machine learning models. Designing
-
at the University of Twente is looking for two PhD candidates to join the research team of Dr. Gaurav Rattan. The positions are funded by the NWO VIDI project Learning on Graphs: Symmetry Meets Structure (LOGSMS
-
Optimization: Mathematical Phylogenetics During this project, you will work on fundamental graph-theoretic and algorithmic problems in mathematical phylogenetics. Job description The Discrete Mathematics and
-
capability graph and a knowledge flow map that highlight unknown connections, adjacent skills and clustering. Analyse data to uncover trends and insights that will contribute to the mapping by applying
-
maps. Knowledge graphs can be used to model these transformations and to link geodata sources to questions. In this project we will apply symbolic and sub-symbolic AI methods to scale this up across
-
that enable efficient problem-solving through energy minimization. In this project, we aim to further explore and exploit the potential of ONNs in embedding graph-based problems, particularly those known to be
-
from reactive to proactive. The goal is to increase transparency and trust in the DNS namespace. Key research activities will include applying machine learning and graph-based techniques to uncover
-
answer maps accordingly. We use knowledge graphs to model these transformations and apply AI methods to scale them up across large map repositories, enabling users to explore many ways maps can be reused
-
. Methodological Approach Candidates will develop and apply state-of-the-art machine learning techniques, including deep learning, representation learning, variational autoencoders, and graph-based models. A strong