Billede af Christian Igel
19972020

Publikationer pr. år

Personlig profil

Kommentarer til publikationsliste

This list of pubications is not fully complete.

For a complete list of older publications as well as papers and software available online please vist my old homepage: http://image.diku.dk/igel

I also maintain a Google Scholar profile: https://scholar.google.dk/citations?user=d-jF4zIAAAAJ

CV

Christian Igel studied Computer Science at the Technical University of Dortmund, Germany. In 2002, he received his Doctoral degree from the Faculty of Technology, Bielefeld University, Germany, and in 2010 his Habilitation degree from the Department of Electrical Engineering and Information Sciences, Ruhr-University Bochum, Germany.

From 2002 to 2010, Christian Igel was a Juniorprofessor for Optimization of Adaptive Systems at the Institut für Neuroinformatik, Ruhr-University Bochum. In October 2010, he has been appointed professor with special responsibilities in machine learning at DIKU. Since December 2014 he is a full professor at DIKU. 

Christian Igel is director of the SCIENCE AI Centre opened in February 2018.

Primære forskningsområder

My main research area is Machine Learning.

Currently I am particularly interested in

  • support vector machines and other kernel-based methods,
  • evolution strategies for single- & multi-objective optimization and reinforcement learning,
  • deep neural networks and stochastic neural networks,
  • PAC-Bayesian analysis of ensemble methods, 

and applications of these methods.

Emneord

  • Det Natur- og Biovidenskabelige Fakultet
  • Datalogi
  • Machine Learning
  • Mønstergenkendelse
  • Classification
  • Optimering
  • Computational Neuroscience

Fingeraftryk

Dyk ned i forskningsemnerne, hvor Christian Igel er aktive. Disse emneetiketter kommer fra dennes persons arbejder. Sammen danner de et unikt fingerprint.
  • 6 Lignende profiler

Samarbejde og topforskningsområder i de sidste fem år

Seneste eksterne samarbejde på lande-/områdeniveau. Dyk ned i detaljerne ved at klikke på prikkerne eller