The Data Science for Engineering group has moved to TU Dortmund

Please note: Our group has moved to TU Dortmund (Faculty of Computer Science, Chair of Safe Autonomous Systems)! The information below is deprecated.

 

 

The Data Science for Engineering group focuses on the development of data-driven and machine learning methods in the context of engineering. In particular, we address the question how data from various sources may be used for the analysis, real-time control and optimization of complex systems. The latter case also includes the simultaneous treatment of multiple conflicting objectives such as maximizing the productivity while minimizing the consumption of resources.

Re­sea­rch

Our research focuses on the following areas

1. Data-driven model reduction, optimization and control of complex dynamical systems

  • Koopman Operator-based approaches
  • Machine learning for prediction and control
  • Reinforcement learning

2. Multiobjective optimization

  • Acceleration of algorithms by structure exploitation
  • Efficient training algorithms for deep learning
  • Applications in the area of machine learning (e.g., sparse regression & neural network training)
  • Efficient solution of expensive problems using model order reduction

About us

Team

We are an interdisciplinary team of computer scientists, mathematicians and engineers performing data science research in the context of complex engineering systems

Te­a­ching

We offer different data-science and ML-oriented courses for computer scientists and students from related fields.

Pro­jects

Our research projects range from basic research to applications of data-driven and machine learning methods to complex engineering systems.

Net­works

SAIL

SAIL is an interdisciplinary and inter-institutional collaboration of Bielefeld University, Paderborn University, Bielefeld University of Applied Sciences and Arts (HSBI) and OWL University of Applied Sciences (TH OWL), funded by MKW NRW.

Pho­QS

The Institute for Photonic Quantum Systems establishes a strategic cooperation model for interdisciplinary research and development of new quantum technologies. It bundles expertise from Paderborn University from the profile areas "Intelligent Technical Systems" and "Optoelectronics and Photonics".

SICP

The SICP - Software Innovation Campus Paderborn at Paderborn University is an interdisciplinary research and innovation network in which companies and science jointly research and implement digital innovations.

CoAI: Co­ope­ra­ti­ve and Co­gni­ti­on-ena­b­led AI

The Joint Research Center on Cooperative and Cognition-enabled AI is Germany’s leading center for interdisciplinary research and innovation on cooperative and cognition-enabled AI that features human-centered, embodied, and real-world agency in the sense that it is capable of acting together with humans in a meaningful and goal-directed manner.

News

03.05.2023

Edi­tor's choice award of the Jour­nal Au­to­ma­ti­ca

Mehr erfahren
26.04.2023

New pa­per in the SI­AM Jour­nal on Scien­ti­fic Com­pu­ting

Mehr erfahren
23.04.2023

New con­fe­rence pa­per (NOL­COS)

Mehr erfahren
14.02.2023

New pre­print on sam­ple ef­fi­cien­cy in re­in­for­ce­ment lear­ning for par­ti­al dif­fe­ren­ti­al equa­ti­ons

Mehr erfahren
26.01.2023

New pre­print on con­vo­lu­ti­o­nal re­in­for­ce­ment lear­ning

Mehr erfahren
22.01.2023

New pre­print on er­ror bounds for ker­nel-ba­sed Ko­op­man ope­ra­tor ap­pro­xi­ma­ti­ons

Mehr erfahren
07.01.2023

New pa­per in Au­to­ma­ti­ca

Mehr erfahren
24.11.2022

New pa­per in Jour­nal of Non­li­ne­ar Sci­ence

Mehr erfahren
17.10.2022

New AI Ju­ni­or Re­sea­rch Group on Mul­ti­cri­te­ria Ma­chi­ne Lear­ning

Mehr erfahren
01.09.2022

New pa­per in Jour­nal of Glo­bal Op­ti­mi­za­ti­on

Mehr erfahren
26.08.2022

New pre­print on sur­ro­ga­te-ba­sed mul­ti­ob­jec­ti­ve op­ti­mi­za­ti­on al­go­rithms with non­li­ne­ar cons­traints

Mehr erfahren
27.07.2022

New pre­print on fast mul­ti­ob­jec­ti­ve gra­di­ent me­thods with Nes­terov ac­ce­le­ra­ti­on

Mehr erfahren
Weitere Neuigkeiten

Jun.-Prof. Dr. Sebastian Peitz

Data Science for Engineering

Raum O4.213
Universität Paderborn
Pohlweg 51
33098 Paderborn