Jan Koutník

My photographJan Koutnik is now a post-doc researcher in Juergen Schmidhuber's group at IDSIA. Jan Koutnik has worked as a teacher and a researcher in Computational Intelligence at Department of Computers at Czech technical University in Prague. He has his master and Ph.D. degrees in Informatics and Computer Science from Faculty of Electrical Engineering at CTU in Prague. His research is focused on artificial neural networks, self-organization, temporal sequences processing and other methods of computational and artificial intelligence applied in various tasks.

Jan Koutnik is now a researcher in Juergen Schmidhuber's group at IDSIA



  • Drchal, J. and Kapraľ, O. and Koutník, J. and Šnorek, M.: Combining Multiple Inputs in HyperNEAT Mobile Agent Controller. vol. 2 nr. , p. 775-783, Springer, Berlin, 2009. ISSN 0302-9743 BibTex, PDF

    In this paper we present neuro-evolution of neural network controllers for mobile agents in a simulated environment. The controller is obtained through evolution of hypercube encoded weights of recurrent neural networks (HyperNEAT). The simulated agent’s goal is to find a target in a shortest time interval. The generated neural network processes three different inputs – surface quality, obstacles and distance to the target. A behavior emerged in agents features ability of driving on roads, obstacle avoidance and provides an efficient way of the target search.

  • Drchal, J. and Koutník, J. and Šnorek, M.: HyperNEAT Controlled Robots Learn How to Drive on Roads in Simulated Environment. In: 2009 IEEE Congress on Evolutionary Computation, p. 6, Research Publishing Services, Singapore, 2009. ISBN 978-1-4244-2959-2 BibTex, PDF

    In this paper we describe simulation of autonomous robots controlled by recurrent neural networks, which are evolved through indirect encoding using HyperNEAT algorithm. The robots utilize 180 degree wide sensor array. Thanks to the scalability of the neural network generated by HyperNEAT, the sensor array can have various resolution. This would allow to use camera as an input for neural network controller used in real robot. The robots were simulated using software simulation environment. In the experiments the robots were trained to drive with imaximum average speed. Such fitness forces them to learn how to drive on roads and avoid collisions. Evolved neural networks show excellent scalability. Scaling of the sensory input breaks performance of the robots, which should be gained back with re-training of the robot with a different sensory input resolution.

  • Zdeněk Buk and Jan Koutník and Miroslav Šnorek: NEAT in HyperNEAT Substituted with Genetic Programming. vol. 5495 nr. , p. 243-252, Springer, Kuopio, Finland, 2009. ISSN BibTex, PDF

    In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.

  • Koutnik, J., Snorek, M.: Temporal Hebbian Self-Organizing Map for Sequences. In: 16th International Conference on Artificial Neural Networks Proceedings (ICANN 2006), Part I, p. 632--641, Springer Berlin / Heidelberg, 2008. ISBN 978-3-540-87535-2 BibTex
  • Koutnik J., Snorek M.: 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 BibTex

    In this paper we present a new self-organizing neural network called Temporal Hebbian Self-organizing Map (THSOM) for modelling of temporal sequences. The network is based on Kohonen's Self-organizing Map but in addition it contains a layer of recurrent synapses trained with Hebb's rule. The network contains two maps. One map is the original spatial map, which performs vector quantization in space. Additional recurrent synapses compose a temporal map, which encodes temporal relations among prototype vectors stored in the spatial map. It is possible to extract a stochastic automaton (Markov Chain) easily from the temporal map using transposition, solution of a system of linear equations and finding of a correct permutations for the neurons to match states of the Markov Chain. The transformation is demonstrated on an experiment, in which a sequence of symbols is generated by randomly generated Markov Chain. A THSOM network is trained with the sequence and from the trained temporal map a transition matrix of the Markov Chain is extracted back. Finally, both transition matrices are compared using a metric. We demonstrate, that THSOM is capable to reconstruct transition matrix of Markov Chain with arbitrary transition matrix.

  • Koutnik J.: Inductive Modelling of Temporal Sequences by Means of Self-organization. In: Proceeding of Internation Workshop on Inductive Modelling (IWIM 2007), p. 269-277, CTU in Prague, 2007. ISBN 978-80-01-03881-9 BibTex, PDF

    In this paper we present a new self-organizing neural network, which builds a spatio-temporal model of an input temporal sequence inductively. The network is an extension of Kohonen's Self-organizing Map with a modified Hebb's rule for update of temporal synapses. The model building behavior is shown on inductive learning of a transition matrix from a data generated by a Markov Chain.

  • Jan Koutnik, Miroslav Šnorek: New Trends in Simulation of Neural Networks. In: Proceedings of 6th EUROSIM Congress on Modelling and Simulation, , Ljubljana, 2007. ISBN 3-901608-32-X BibTex

    In this paper actual simulation techniques and simulation systems for artificial neural networks are compared. We focus on neural network simulators that allow a user easy design of new neural networks. There are several simulation strategies that can be exploited by modern neural network simulators described. We considered the synchronous simulation as the most effective for parallel systems like artificial neural networks. Examples of general simulation systems that can be used for simulation of neural networks are mentioned. Current neural network simulators commonly depend on a type of neural network simulated and cannot be easily extended to simulate a different or a neural network with a brand new architecture and function. Universal simulation tools seem to be suitable for network design but do not support connectionism natively. The missing language constructions and tools for native support of connecting objects in the simulation lead us to design a new simulation tool SiMoNNe - Simulator of Modular Neural Networks, which allows easy design and simulation of neural networks using a high level programming language. The language itself is object oriented with weak type control. It supports native connection of simulated neurons, layers, modules and networks, matrix calculations, easy control of simulation parameters using expressions, re-usability of the result as a source code and more. The language is interactive and allows connection of a GUI to the SiMoNNe core.

  • Drchal J., Kordík P., Koutník J.: Visualization of Diversity in Computational Intelligence Methods. In: Proceedings of 2nd ISGI, International CODATA Symposium on Generalization of Information, p. 20-34, CODATA Germany, 2007. ISBN 978-3-00-022382-2 BibTex
  • Trnka R., Koutnik J.: 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, 2006. ISSN 0033-2852 BibTex

    Progressive methods of data evaluation based on recent artificial neural networks are introduced to the field of psychology in the current study. Artificial neural networks techniques work on different basis than the classical statistical methods. Particularly, the Kohonen's Self-Organizing Map (SOM), the Modified Group Method of Data Handling (GMDH), and the recent Group of Adaptive Models Evolution (GAME) were used in this study for a self-organized clustering of the measured data and for an analysis of factor significance. Significance of seven various factors for facial expression decoding accuracy was assessed. Gender was considered to be the most significant factor for the correct recognition of facial expressions. Place of origin yielded the second highest significance. Results indicate women to be better decoders than men and persons growing up in urban areas to be better decoders than persons growing up in rural areas.

  • Koutnik J., Mazl R., Kulich M.: 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 BibTex, PDF

    In this paper, we present a new parallel self-organizing technique for three dimensional shape reconstruction for mobile robotics. The method is based on adaptive input data decomposition, parallel shape reconstruction in decomposed clusters using Kohonen Self-Organizing Map, which creates mesh representation of the input data. Afterwards, the sub-maps are joined together and the final mesh is re-optimized. Our method overcomes a problem of fitting one mesh to complex non-continuous shapes like building interiors. The method allows to process unordered data collected by mobile robots. The method is easily paralelizable and gives promising results.

  • Koutnik J., Snorek M.: 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 BibTex, poster

    In this paper we introduce a self-organizing neural network that is capable of recognition of temporal signals. Conventional self-organizing neural networks like recurrent variant of Self-Organizing Map provide clustering of input sequences in space and time but the identification of the sequence itself requires supervised recognition process, when such network is used. In our network called TICALM the recognition is expressed by speed of convergence of the network while processing either learned or an unknown signal. TICALM network capabilities are shown on an experiment with handwriting recognition.

  • Koutnik J., Snorek M.: 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. ISBN BibTex

    In this paper we introduce technique how a neural network can generate a Hidden Markov Chain. We use neural network called Temporal Information Categorizing and Learning Map. The network is an enhanced version of standard Categorizing and Learning Module (CALM). Our modifications include Euclidean metrics instead of weighted sum formerly used for categorization of the input space. Construction of the Hidden Markov Chain is provided by turning steady weight internal synapses to associative learning synapses. Result obtained from testing on simple artificial data promises applicability in a real problem domain. We present a visualization technique of the obtained Hidden Markov Chain and the method how the results can be validated. Experiments are being performed.

  • Koutnik J., Snorek M.: Efficient Simulation of Modular Neural Networks. In: Proceedings of the 5th EUROSIM Congres Modelling and Simulation, Vienna: EUROSIM-FRANCOSIM-ARGESIM, 2004. ISBN 3-901608-28-1 BibTex, PDF

    In this paper we describe a new language for efficient simulation of modular neural networks called SiMoNNe. After an unsuccessful search for a suitable simulation environment we designed a simulator driven by a high level programming language which allows easy and fast creation, simulation and testing of various neural network architectures. Not only modular neural networks can be simulated but also well known conventional neural network paradigms can be simulated by SiMoNNe.

  • Koutnik J., Snorek M.: 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 BibTex, PDF

    Modifications of an existing neural network called Categorizing and Learning Module (CALM) that allow learning of temporal sequences are introduced in this paper. We embedded an associative learning mechanism which allows to look into the past when classifying present stimuli. We have built in the Euclidean metrics instead of the weighted sum found in the original learning rule. This improvement allows better discrimination in case of learning low dimensional patterns in the temporal sequences. Results were obtained from testing the enhanced module on simple artificial data. These experiments promise applicability of the enhanced module in a real problem domain.

  • Kubalik J., Koutnik J.: Automatic Generation of Fuzzy Rule Based Classifiers by Evolutionary Algorithms. Intelligent and Adaptive Systems in Medicine vol. nr. , p. 197-206, Praha: CVUT FEL, 2003. ISSN 1213-3000 BibTex
  • Koutnik J., Snorek M.: 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 BibTex, PDF
  • Kubalik J., Koutnik J., Rothkrantz L. J. M.: Grammatical Evolution with Bidirectional Representation. In: Genetic Programming, Proceedings of EuroGP'2003, p. 354-363, Berlin: Springer, 2003. ISBN 3-540-00971-X BibTex, PDF
  • Brunner J., Koutnik J.: Simonne - Simulator of Modular Neural Networks. Neural Network World vol. 12 nr. 3, p. 267-278, , 2002. ISSN 1210-0552 BibTex
  • Koutnik J., Brunner J., Snorek M.: 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, 2002. ISBN 83-9176-831-7 BibTex, PDF