Sort by
Refine Your Search
-
Listed
-
Country
-
Employer
- CNRS
- Aalborg University
- ETH Zürich
- French National Research Institute for Sustainable Development
- Friedrich Schiller University Jena
- Georgetown University
- Japan Agency for Marine-Earth Science and Technology
- Johns Hopkins University
- King Abdullah University of Science and Technology
- Massachusetts Institute of Technology
- Oak Ridge National Laboratory
- University of Amsterdam (UvA)
- University of Amsterdam (UvA); yesterday published
- University of California Davis
- University of Colorado
- University of Idaho
- University of Luxembourg
- 7 more »
- « less
-
Field
-
associated with phenotypic (biomechanical and metabolomics) traits. Estimate locus-specific effect sizes and quantifying genetically-driven phenotypic variations. Develop Bayesian models and/or deep learning
-
descent, random forests, etc.) and deep neural network architectures (ResNet and Transformers). Preferred Qualifications: Knowledge of Approximate, Local, Rényi, Bayesian differential privacy, and other
-
features to behavior using GLMMs/Bayesian models; conduct sensitivity and robustness checks. * Method validation: benchmark alternative pipelines (filters, burst detectors, forward/inverse models); perform
-
communication and collaboration skills Preferred: Experience with simulation-based inference and Bayesian methods Familiarity with cosmological simulations or observational cosmology ML architecture design and
-
individual rates of ageing. Role You will extend BrainAGE from global estimates to regional normative models using Bayesian regression and GAMLSS to derive age- and region-specific reference distributions
-
mathematical information science approaches, such as scientific machine learning. Potential research topics include, but are not limited to: (1) Bayesian estimation of 3D velocity structure models using ocean
-
experimental methods. Develop and apply methods for demultiplexing, normalization/QC, effect-size estimation, biological inference, and predictive modeling. Contribute to biological manuscripts and methods
-
to implement advanced computational pipelines, including machine learning, deep learning, Bayesian inference, and probabilistic mixed membership modeling for innovative research. · Contribute
-
areas Biomedical applications, social determinants of health or other demographic health areas Spatial microsimulation, spatially weighted regression, combinatorial optimization or Bayesian network
-
project include two aspects: (1) based on the cutting-edge technologies from deep learning, computer vision or physics-informed machine learning, develop robust surrogate forward models to predict