Knowledge Discovery and Synthesis
The "Knowledge Discovery and Synthesis" group is investigating methods for identifying potentially complex patterns in data, and methods for synthesizing information from several sources. The spectrum of our work ranges from meta-analysis techniques for clinical trials to machine learning techniques, in particular artificial intelligence/deep learning, for integrating molecular and clinical data.
AG Machine Learning
- Machine Learning (esp. Deep Learning)
- Deep Generative Models
- Machine Learning (esp. Deep Learning)
- Distributed Data
- Deep Generative Models
- Machine Learning (esp. Deep Learning)
- Neural Differential Equations
- Generative Models
- Machine Learning (esp. Deep Learning)
- Feature Learning in High-Dimensional Molecular-Diagnostic Data
- Machine Learning (esp. Deep Learning)
- Resilience and Vulnerabilty
- Age-Period-Cohort Analysis
- Algorithms, (esp. in the Field of Deep Learning)
- Software Development and API Design
- Machine Learning (esp. Deep Learning)
- Machine Learning (esp. Deep Learning)
- Deep Generative Models
- Deep Generative Models
- Design of Single Cell RNA-Seq Experiments
- Longitudinal Data Modeling
- Modeling of Clinical Registry Data
- Modeling of Distributed Data
AG Meta-Analyze
- Meta-Analysis
- Meta-Analysis of Diagnostic Accuracy Studies
- Meta-analysis
- Network Meta-analysis
- Software Development
- Meta-Analysis
- Network Meta-Analysis
- Meta-Analysis of Diagnostic Accuracy Studies
- Meta-Analysis
- Software Development
AG STRATOS
- STRATOS
-
Multivariable Model-Building in Regression Models
-
Model Stability and Shrinkage
-
Simulation Studies
-
Variable Selection
-
Simulation Studies
-
High-Dimensional Data
Alumni
Caroline Broichhagen
Federico Bonofiglio
