Sort by
Refine Your Search
-
candidate, with a strong background in the development of machine learning methods for bioinformatics. The project focuses on the development of new neural network architectures to perform inference
-
/landscape openness/deforestation), sedimentology analysis for reconstruction of past human occupation and pollution, and charcoal analysis for inference of past fire history, metallurgy, and land-use
-
learning and/or statistics, Linux Desired skills: strong track record of papers on whole brain modeling, experience working with EEG (and/or MEG), fMRI, MRI + DTI (including tractography), simulation-based
-
Two-year postdoc position (M/F) in signal processing and Monte Carlo methods applied to epidemiology
. To that aim, both Stein-based bilevel optimization, empirical Bayesian and unsupervised deep learning approaches will be considered. The recruited postdoc researcher will tackle both implementation challenges
-
energy efficiency during the training process and (ii) science yield (sensitivity / resolution) during inference. A key aspect is to benefit from hybrid HPC + AI approaches within the workflows
-
modeling and simulation, and statistical inference (lead by mathematicians and biologists) - The recruited postdoc will be asked to work in the labs on a daily basis. - The recruited postdoc will be expected
-
in the use and exploitation of high spatial and temporal resolution remote sensing data. An interest in causal discovery and inference is more than welcome. The candidate will be required to interact
-
on the statistical inference of Linear Mixed Models (LMMs). The project's goal is to develop a new breed of Mixed Effects Neural Networks (MENN) for Genome InterpretationI that take the best from both worlds, merging
-
to process improvements, project planning and tracking, progress reviews and demonstrations, and coordination with other teams. Exa-SofT mission Task T4.4 in WP4 of the Exa-SofT project deals with
-
all these systems, is to understand how a collective dynamics emerges at the macroscopic scale and can be described through a small number of parameters, without keeping track of all the microscopic