Sort by
Refine Your Search
-
Category
-
Employer
-
Field
-
, particularly ADHD, using large-scale genetic, imaging, and epidemiological data from Denmark and other countries. You will apply advanced analytical approaches, including deep learning and machine learning, to
-
machine learning, preferably experience in probabilistic modeling, Bayesian machine learning, or graph representation learning. Programming skills (e.g., Python) and experience with deep learning
-
which you will be automatically redirected to an external site after 5 seconds) Save job Click to add the job to your shortlist Send job Job Details Are you interested in using machine learning to
-
to Danish data sources (e.g., registry data, surveys, and organisations). Your competencies Digital methods such as machine learning based classification, computational text analysis, network
-
of up to 2 years. The place of employment will be in Odense. Research profiles and tasks We are looking for a candidate with a background in computational social sciences, machine learning or data
-
project, you will design and implement a hyperspectral imaging system tailored to bulk forensic trace analysis and develop chemometric and machine-learning models for material identification and
-
development Machine learning for material assessment and property prediction Finite element modelling, structural optimisation and experimental validation Fabrication and testing of full scale
-
. Your competencies Applicants must have a strong technical background, ideally in computer science, software engineering, human-computer interaction, Medialogy, AI, machine learning, or a related field
-
, the project may include network analysis, geospatial analysis, scenario modelling, uncertainty analysis, machine learning and other AI-supported approaches. The candidate will build on selected
-
structured, well-documented way that supports benchmarking, reproducibility, and reuse by others. Essential: Strong data analysis and machine learning skills and experience with PyTorch (or equivalent