Dipl.-Inform. Patrick Koch

Research Associate
Cologne University of Applied Sciences - Campus Gummersbach
Faculty of Computer Science and Engineering
Institute of Computer Science
Room 1.112
Steinmüllerallee 1
51643 Gummersbach

www.gm.fh-koeln.de/~pkoch

Curriculum Vitae:

Patrick was born in 1982 and studied Computer Science at the University of Paderborn. His main research interests include the application of Computational Intelligence techniques in Data Mining. Patrick is currently working on topics as parameter tuning, feature selection and optimization under limited budgets. During his studies, Patrick worked as a research assistant at the LS11 chair of the Dortmund university. From 2005 until 2009 he was also elected board member of the Paderborn Center for Parallel Computing (PC²). He worked as an intern at the German Research Center for Artificial Intelligence (DFKI) in Saarbrücken and at the Wincor Nixdorf International GmbH in Paderborn. Since his graduation from the university of Paderborn in December 2008 Patrick is working as a research associate at the Cologne University of Applied Sciences in the BMBF funded project SOMA of Prof. Dr. Wolfgang Konen. Patrick is currently writing his PhD thesis at the Leiden Institute of Advanced Computer Science (LIACS) in the Natural Computing Group headed by Prof. Dr. Thomas Bäck.

Selected Publications:

  1. P. Koch and W. Konen: Efficient Sampling and Handling of Variance in Tuning Data Mining Models, submitted to international conference on Parallel Problem Solving from Nature 2012, Taormina, Italy, September 2012.
  2. M. Thill, P. Koch, W. Konen: Reinforcement Learning with N-tuples on the Game Connect-4, submitted to international conference on Parallel Problem Solving from Nature 2012, Taormina, Italy, September 2012.
  3. P. Koch, B. Bischl, O. Flasch, T. Bartz-Beielstein, and W. Konen: Tuning and Evolution of Support Vector Kernels, to appear: Journal of Evolutionary Intelligence, Springer, Special issue on Evolutionary Kernel Machines, 2012
  4. W. Konen, P. Koch, O. Flasch, T. Bartz-Beielstein, M. Friese, and B. Naujoks: Tuned data mining: A benchmark study on different tuners, in proceedings of the Genetic and Evolutionary Computation Conference 2011, Dublin, Ireland, July 2011
  5. W. Konen and P. Koch: The slowness principle: SFA can detect different slow components in non-stationary time series, International Journal of Innovative Computing and Applications, vol. 3 (1), pages 3-10, Inderscience, 2011.
  6. W. Konen, P. Koch, O. Flasch, and T. Bartz-Beielstein: Parameter-Tuned Data Mining: A General Framework. In: F. Hoffmann, E. Hüllermeier (eds.), Proceedings 20. Workshop Computational Intelligence, Dortmund. Universitätsverlag Karlsruhe, December 2010.
  7. P. Koch, W. Konen, O. Flasch, and T. Bartz-Beielstein: Optimizing Support Vector Machines for Stormwater Prediction. Technical Report TR10-07 at the Algorithm Engineering Group of TU Dortmund, Proceedings of the Workshop on Experimental Methods for the Assessment of Computational Systems (WEMACS 2010), held in conjunction with the 11th International Conference on Parallel Problem Solving From Nature (PPSN), Krakow, Poland, September 2010.
  8. P. Koch, W. Konen, and K. Hein: Gesture Recognition on Few Training Data using Slow Feature Analysis and Parametric Bootstrap, in proceedings of World Congress of Computational Intelligence 2010, Barcelona, Spain, July 2010.
  9. W. Konen and P. Koch: How slow is slow? SFA detects signals that are slower than the driving force, in proceedings of BIOMA 2010 (Bioinspired Optimization Methods and their Applications), Ljubljana, Slovenia, May 2010.
  10. O. Flasch, T. Bartz-Beielstein, P. Koch and W. Konen: Genetic Programming Applied to Predictive Control in Environmental Engineering. In: F. Hoffmann, M. Reischl (eds.), Proceedings 19. Workshop Computational Intelligence, Dortmund. Universitätsverlag Karlsruhe, December 2009.
  11. O. Kramer and P. Koch: Rake Selection: A Novel Evolutionary Multi-Objective Optimization Algorithm, Proceedings of 32nd Annual Conference on Artificial Intelligence, September 2009, Paderborn, Germany.
  12. P. Koch, O. Kramer, N. Beume and G. Rudolph: On the Hybridization of SMS-EMOA and Local Search for Continuous Multiobjective Optimization, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) July 2009, Montréal, Canada.
  13. O. Kramer and P. Koch, Self-Adaptive Crossover, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2007, London, UK

Links:


Leiden Institute of Advanced Computer Science
COSA Kolloquium
CIOP Project
Ruxandra Stoean
Catalin Stoean
Mensa Plan