-
, recurrent memory, Bayesian modelling, uncertainty quantification and machine learning systems. Emphasis will be on methods that design and implement new architectures for (auto-regressive) sequence modelling
-
(PINNs) and surrogate modelling Time-series modelling and anomaly detection Bayesian methods and uncertainty quantification Graph Neural Networks (GNNs) Spatiotemporal data engineering Digital twins and
-
anomaly detection Bayesian methods and uncertainty quantification Graph Neural Networks (GNNs) Spatiotemporal data engineering Digital twins and simulation Demonstrated Applied AI for Healthcare and
-
modelling analyses, including differential gene expression analysis, microbiome diversity analyses, host–microbiome association testing, metagenome-wide association analyses (mGWAS), hierarchical Bayesian
-
Elhoseiny, Code: https://github.com/yli1/CLCL Uncertainty-guided Continual Learning with Bayesian Neural Networks (ICLR’20), Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach, Code: https
-
processes of the study systems of our collaborators. Core components of the research involve, among others, Bayesian hierarchical modelling, shrinkage methods, machine learning (ML) or dimension reduction