Jan Koutnik is currently a postdoctoral researcher working in Juergen Schmidhuber's group at IDSIA. He is focused on research in machine learning, namely artificial neural networks and evolutionary algorithms.
source: home archive

He obtained his Ph.D. computer science in the year 2008 from Faculty of Electrical Engineering, Czech Technical University in Prague, where he worked as an assistant professor at the Department of Computer Science and Engineering, while being member of Computational Intelligence Group research group. He czeched out and joined IDSIA in April 2009.

He likes cycling (mountain and road), amateur photography (especially portraits). Check out his web log, containing tricks for computers and real life.


  1. Faustino Gomez, Jan Koutnik, and Juergen Schmidhuber (2012). Complexity Search for Compressed Neural Networks To appear in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-12, Philadelphia)
  2. Jan Koutnik, Juergen Schmidhuber and Faustino Gomez. A Frequency Encoding Domain for Neuroevolution. Under review in Neural Computation, MIT Press, Cambridge, MA, USA
  3. Tobias Glasmachers, Jan Koutnik and Juergen Schmidhuber (2012). Kernel Representations for Evolving Continuous Functions. Journal of Evolutionary Intelligence, Springer, Germany
  4. Vincent Graziano, Jan Koutnik and Juergen Schmidhuber (2011). Unsupervised Modeling of Partially Observable Environments. Proceedings of the European Conference on Machine Learning (ECML-11, Athens, Greece).
  5. Jan Koutnik, Faustino Gomez, and Juergen Schmidhuber (2010). Evolving Neural Networks in Compressed Weight Space. In Proceedings of the Conference on Genetic and Evolutionary Computation (GECCO-10) .
  6. Jan Koutnik, Faustino Gomez, and Juergen Schmidhuber (2010). Searching for Minimal Neural Networks in Fourier Space. In Proceedings of the Third Conference on Artificial General Intelligence (AGI-10, Lugano, Switzerland).
  7. Julian Togelius, Sergey Karakovskiy, Jan Koutnik and Juergen Schmidhuber (2009). Super Mario Evolution. Proceedings ot the IEEE Symposium on Computational Intelligence and Games (CIG).
  8. Publications at CTU in Prague

  9. Pavel Kordik, Jan Koutnik, Jan Drchal, Oleg Kovarik, Miroslav Cepek, Miroslav Snorek (2010). Meta-learning approach to neural network optimization. Neural Networks, 23(4), p. 568-582.
  10. Jan Drchal, Ondrej Kapral, Jan Koutnik and Miroslav Snorek (2009). Combining Multiple Inputs in HyperNEAT Mobile Agent Controller. In: ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks, vol. 2, p. 775-783, Springer, Berlin, ISSN 0302-9743
  11. Jan Drchal, Jan Koutnik and Miroslav Snorek (2009). HyperNEAT Controlled Robots Learn How to Drive on Roads in SimulatedEnvironment. In: 2009 IEEE Congress on Evolutionary Computation, p. 6, Research Publishing Services, Singapore, ISBN 978-1-4244-2959-2
  12. Zdenek Buk, Jan Koutnik and Miroslav Snorek (2009). NEAT in HyperNEAT Substituted with Genetic Programming. In:Adaptive and Natural Computing Algorithmsvol.5495, nr. , p. 243-252, Springer, Kuopio, Finland
  13. Jan Koutnik and Miroslav Snorek (2008). Temporal Hebbian Self-Organizing Map for Sequences. In: 16th International Conference on Artificial Neural Networks Proceedings (ICANN 2008), Part I, p. 632--641, Springer Berlin / Heidelberg, ISBN 978-3-540-87535-2
  14. Jan Koutnik and Miroslav Snorek (2007). Extraction of Markov Chain from Temporal Hebbian Self-organizing Map. In: Proceedings of the International Workshop on Modelling and Simulation in Management, Informatics and Control, , 2007. ISBN 978-80-8070-807-8
  15. Jan Koutnik: Inductive Modelling of Temporal Sequences by Means of Self-organization (2007). In: Proceeding of Internation Workshop on Inductive Modelling (IWIM 2007), p. 269-277, CTU in Prague, ISBN 978-80-01-03881-9
  16. Jan Koutnik and Miroslav Snorek: New Trends in Simulation of Neural Networks (2007). In: Proceedings of 6th EUROSIM Congress on Modelling and Simulation ,Ljubljana, ISBN 3-901608-32-X
  17. Jan Drchal, Pavel Kordik and Jan Koutnik (2007). Visualization of Diversity in Computational Intelligence Methods. In: Proceedings of 2nd ISGI, International CODATA Symposium on Generalization of Information, p. 20-34, CODATA Germany, ISBN 978-3-00-022382-2
  18. Radek Trnka and Jan Koutnik (2006). Application of the Kohonen's self-organizing map and the group of adaptive models evolution in social cognition research. Psychologia vol. 4 nr. , p. 238-251, Department of Cognitive Psychology in Education, Psychologia Society, Kyoto University, Kyoto 606-8501, Japan, ISSN 0033-2852
  19. Jan Koutnik, Roman Mazl and Miroslav Kulich (2006). Building of 3D Environment Models for Mobile Robotics Using Self-organization. In: Parallel Problem Solving from Nature - PPSN-IX. Heidelberg, p. 721-730, Springer, 2006. ISBN 3-540-38990-3
  20. Jan Koutnik and Miroslav Snorek (2006). Self-Organizing Neural Networks for Signal Recognition. In: 16th International Conference on Artificial Neural Networks Proceedings (ICANN 2006) , Part I, p. 406-414, Springer Berlin / Heidelberg, 2006. ISBN 978-3-540-38625-4
  21. Jan Koutnik and Miroslav Snorek (2005) .Neural Network Generating Hidden Markov Chain. In: Adaptive and Natural Computing Algorithms - Proceedings of the International Conference in Coimbra, p. 518-521, Wien: Springer, 2005.
  22. Jan Koutnik and Miroslav Snorek (2004): Efficient Simulation of Modular Neural Networks. In: Proceedings of the 5th EUROSIM Congres Modelling and Simulation, Vienna: EUROSIM-FRANCOSIM-ARGESIM, ISBN 3-901608-28-1
  23. Jan Koutnik and Miroslav Snorek: Single Categorizing and Learning Module for Temporal Sequences. In: Proceedings of the International Joint Conference on Neural Networks, p. 2977-2982, Piscataway: IEEE, 2004. ISBN 0-7803-8360-5
  24. Jiri Kubalik and Jan Koutnik (2003): Automatic Generation of Fuzzy Rule Based Classifiers by Evolutionary Algorithms. In: Intelligent and Adaptive Systems in Medicine, p. 197-206, Praha: CVUT FEL, ISSN 1213-3000
  25. Jan Koutnik and Miroslav Snorek (2003): Enhancement of Categorizing and Learning Module (CALM) - Embedded Detection of Signal Change. In: IJCNN 2003 Conference Proceedings, p. 3233-3237, Piscataway: IEEE, 2003. ISBN 0-7308-7899-7
  26. Jiri Kubalik, Jan Koutnik and Leon J. M. Rothkrantz: Grammatical Evolution with Bidirectional Representation. In: Genetic Programming, Proceedings of EuroGP'2003, p. 354-363, Berlin: Springer, 2003. ISBN 3-540-00971-X
  27. Jan Brunner and Jan Koutnik (2002): SiMoNNe - Simulator of Modular Neural Networks. In: Neural Network World, vol. 12 nr. 3, p. 267-278, ISSN 1210-0552
  28. Jan Koutnik, Jan Brunner and Miroslav Snorek (2002): The GOLOKO Neural Network for Vision - Analysis of Behavior. In: Proceedings of the International Conference on Computer Vision and Graphics, p. 437-442, Gliwice: Silesian Technical University, ISBN 83-9176-831-7


Compressed Neural Networks

In state-of-the-art neuroevolution, researchers look for efficient way of encoding the artificial neural networks in strings (genomes) of symbols (genes) in order to reduce the search space of such genomes. Jan's recent research in indirect encoding lead in a method, which describes a neural network weight matrix by a limited set of it's frequency coefficient. The genome consists of a limited set of frequency coefficients that transform to the weight matrix using inverse Fourier-type frequency transform.

The weight matrix get decorrelated after transformed to the frequency domain. The complexity of a genome could be pushed down by encoding the frequency coefficients with a limited number of bits. If the space of coefficients is small (say less than 32 bits), then it could be searched exhaustively starting from the shortest bit strings.

Surprisingly, some of the well known benchmarks could be solved with networks described by fairly short bit-string. For example, single-pole balancing controller consisting of one neuron could be described by just 1 bit (positive constant weights matrix), which means that single-pole benchmark no longer exists.

Evolutionary Robotics

Temporal Hebbian Self-organizing Map

Temporal Hebbian Self-organizing Map is a recurrent extension of Kohonen's SOM. Additional layer of full recurrent connections among the nodes is trained in a Hebbian way. The connections accumulate first-order statistics of transitions between states represented by the neurons, while placing the neurons into centroids of clusters using the input connections. The network clusters the data in both input space and time. The initial THSOM model Hebbian training was improved by Ferro et al. introducing neighborhood in the temporal connections.