We combine strong mathematical background and state-of-art machine learning tools with emphasis on deep neural networks: 

 Current Projects

• Reliable predictions and forecasting: uncertainty quantification (risk assessment).
  (Members: Pavel Gurevich, Hannes Stuke)

• Hysteretic neural networks 
  (Members: Pavel Gurevich, Hannes Stuke, Nikita Begun, Zongxiong Chen
  Collaboration partner: Prof. Dimitri Rachinskii (University of Texas at Dallas)) 

• Representation learning for time series
  (Members: Pavel Gurevich, Hannes Stuke, Yu He,
  Collaboration partner: Paul Alexandru Bucur (ThyssenKrupp))

• Active learning
  (Members: Pavel Gurevich, Hannes Stuke, David Mickisch)

• Reinforcement learning
  (Members: Pavel Gurevich, Hannes Stuke, Florian Dorner)

• Computationally assisted diagnosis of Alzheimer's dementia
  (Members: Pavel Gurevich, Hannes Stuke,
  Collaboration partners: Prof. Helmut Hildebrandt (Municipal Hospital of Bremen-Ost, University of Oldenburg), Dr. Heiner Stuke (Charité Berlin)) 

•  Bayesian methods for time series classification  
   (Members: Pavel Gurevich, Hannes Stuke, Julian Stastny)

•  Machine Learning, Critical Mathematical Economics and Progressive Policy 
   (Members: Pavel Gurevich, Hannes Stuke, Johannes Buchner)

Cooperation

• ThyssenKrupp (Paul Alexandru Bucur)
  Product quality assessment with machine learning methods

• Municipal Hospital of Bremen-Ost, University of Oldenburg (Prof. Helmut Hildebrandt)
  Computationally assisted diagnosis of Alzheimer's dementia with neuropsychologic testing

• Charité Berlin (Dr. Heiner Stuke)
• University of Texas at Dallas (Prof. Dimitri Rachinskii)
  Hysteretic neural networks