Stefan Kremer

Photo of Stefan Kremer
Phone number: 
Reynolds 3309

My lab works on the problem of learning to recognize, categorize and generate structural patterns based on examples (this is called induction).  Structural patterns refers to patterns in data that are not easily represented by a fixed-length sequence of numbers (i.e. a vector). Examples:  English text, the shape of a molecule, a sequence of DNA, a radio signal, a system log, a video.  The lab is problem-driven (not solution driven), so we use a number of methods and tools like artificial neural networks, support vector machine, deep belief networks, hidden Markov models, evolutionary algorithms and deep learning.  Problems are drawn from a variety of domains, but problems related to biology are especially welcome.

  • deep-learning
  • deep belief networks
  • recurrent networks
  • spatio temporal pattern recognition
  • pattern induction
  • bioinformatics
  • DOI: 10.1111/mec.13219
  • DOI: 10.1016/j.dsp.2015.08.007
  • DOI: 10.1162/089976601300014538
  • DOI: 10.1162/089976603321780281
  • ISBN: 978-0-7803-5369-5