All publications


  • Martin Šlapák, Roman Neruda: Multiobjective Genetic Programming of Agent Decision Strategies. In: Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014, p. 173-182, Springer International Publishing, 2014. ISBN 978-3-319-08155-7 BibTex, PDF


  • Roman Neruda, Martin Šlapák: Evolving Decision Strategies for Computational Intelligence Agents. In: Proceedings of ICIC 2012 - Lecture Notes in Artificial Inteligence, , 2012. ISBN BibTex, PDF
  • Oleg Kovářík, Richard Málek: Meta-learning and meta-optimization. , 2012 BibTex, PDF


  • Martin Šlapák: Genetics in decision behaviour of computational agents. In: Proceedings of Mendel 2011 - 17th International Conference on Soft Computing, , 2011. ISBN BibTex, PDF


  • Zahradník, J., Skrbek, M.: Classification of Spatio-Temporal Data. In: Proceedings of the 7th EUROSIM Congress on Modelling and Simulation, Vol. 2: Full Papers, p. 1168-1173, Praha: Department of Computer Science and Engineering, FEE, CTU in Prague, September 2010. ISBN 978-80-01-04589-3 BibTex, PDF

    This paper presents a new approach in spatio-temporal data classification. This classification can be used in many branches including robotics, computer vision or medical data analysis. Due to easy transformation of time dimension of spatio-temporal data into the phase of complex number, the presented approach uses complex numbers. The classification is based on a complex-valued neural network with multilayer topology. The paper proposes an extension of complexvalued backpropagation algorithm, which uses activation function applying nonlinearity on the amplitude only (preserving the phase) instead of commonly used activation function applying non-linearities on the real and the imaginary part separately. In order to transform the input data into complex numbers, a new coding technique is presented. It encodes the time-dimension into phase of complex number and space-dimensions into amplitude of complex numbers. Another task is to develop output coding, that would allow the classification from complex numbers. It is solved with introduction of one-of-N coding extension into complex numbers, which is used as network’s output coding. This approach is verified in application of hand-written character recognition, using the data collected during the writing process. The simulation results of this application are presented in the paper.

  • Podhorský P., Skrbek M.: Simulation and Genetic Evolution of Spiking Neural Networks. In: 7th EUROSIM Congress on Modelling and Simulation, Praha: Czech Technial University in Prague, September 2010. ISBN BibTex


  • 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.

  • Aleš Pilný, Wolfgang Oertel, Pavel Kordík, Miroslav Šnorek: Correlation-based Feature Ranking in Combination with Embedded Feature Selection. vol. nr. , p. , , 2009. ISSN BibTex, PDF

    Most of Feature Ranking and Feature Selection approaches can be used for categorial data only. Some of them rely on statistical measures of the data, some are tailored to a specific data mining algorithm (wrapper approach). In this paper we present new methods for feature ranking and selection obtained as a combination of the above mentioned approaches. The data mining algorithm (GAME) is designed for numerical data, but it can be applied to categorial data as well. It incorporates feature selection mechanisms and new methods, proposed in this paper, derive feature ranking from final data mining model. The rank of each feature selected by model is computed by processing correlations of outputs between neighboring model’s neurons in different ways. We used four different methods based on fuzzy logic, certainty factors and simple calculus. The performance of these four feature ranking methods was tested on artificial data sets, on well known Ionosphere data set and on well known Housing data set with continuous variables. The results indicated that the method based on simple calculus approach was significantly worse than other three methods. These methods produce ranking consistent with recently published studies.

  • Kordík P.: GAME - Hybrid Self-Organizing Modeling System based on GMDH. Springer-Verlag, Berlin, Heidelberg, Czech Technical University in Prague, FEE, Dep. of Comp. Sci. and Computers, 2009 BibTex, PDF

    In this chapter, an algorithm to construct hybrid self-organizing neural network is proposed. It combines niching evolutionary strategies, nature inspired and gradient based optimization algorithms (Quasi-Newton, Conjugate Gradient, GA, PSO, ACO, etc.) to evolve neural network with optimal topology adapted to a data set. The GAME algorithm is something in between the GMDH algorithm and the NEAT algorithm. It is capable to handle irrelevant inputs, short and noisy data samples, but also complex data such as "two intertwined spirals" problem. The self-organization of the topology allows it to produce accurate models for various tasks (classification, prediction, regression, etc.). Bencharking with machine learning algorithms implemented in the Weka software showed that the accuracy of GAME models was superior for both regression and classification problems. The most successful configuration of the GAME algorithm is not changing with problem character, natural evolution selects all important parameters of the algorithm. This is a significant step towards the automated data mining.

  • 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.


  • NOVÁK D., PILNÝ A., KORDÍK P., HOLIGA Š., POŠÍK P., ČERNÝ R., BRZEZNÝ R.: Analysis of Vestibular-Ocular Reflex by Evolutionary Framework. vol. nr. , p. 452-461, Springer, 2008. ISSN BibTex, PDF

    In this paper the problem of analysis of eye movements using sinu- soidal head rotation test is presented. The goal of the method is to discard au- tomatically the effect of the fast phase-saccades and consequently calculate the response of vestibular system in the form of phase shift and amplitude. The com- parison of threshold detection and inductive models trained on saccades is car- ried out. After saccades detection we are left with discontinuous signal segments. This paper presents an approach to align them to form a smooth signal with the same frequencies that were originally present in the source signal. The approach is based on a direct estimation of the signal component parameters using the evolutionary strategy with covariance matrix adaptation. The performance of evolutionary approach is compared to least-square multimodal sinus fit. The experimental evaluation on real-world signals revealed that threshold saccades detection with combination of the evolutionary strategy is robust, scalable and reliable method

  • : Behaviour of FeRaNGA Method for Feature Ranking During Learning Process Using Inductive Modelling. Proceedings of the 2nd International Conference on Inductive Modelling. Kiev: Ukr. INTEI vol. nr. , p. , , 2008. ISSN BibTex, PDF

    Nowadays a Feature Ranking (FR) is commonly used method for obtaining information about a large data sets with various dimensionality. This knowledge can be used in a next step of data processing. Accuracy and a speed of experiments can be improved by this. Our approach is based on Artificial Neural Networks (ANN) instead of classical statistical methods. We obtain the knowledge as a by-product of Niching Genetic Algorithm (NGA) used for creation of a feedforward hybrid neural network called GAME. In this paper we present a behaviour of FeRaNGA (Feature Ranking method using Niching Genetic Algorithm(NGA)) during a learning process, especially in every layer of generated GAME network. We want to answer how important is NGA configuration and processing procedure for FR results because behaviour of GA is nondeterministic and thereby were results of FeRaNGA also indefinitive. This method ranks features depending on a percentage of processing elements that survived a selection process. Processing elements transforms parent input features to an output. The selection process is realized by means of NGA where units connected to the least significant features starve and fade from population. To obtain the best results and to find optimal configuration is behaviour of the FeRaNGA algortithm tested using various parameters of NGA and number of ensemble GAME models on well known artificial data sets.

  • Ales Pilny, Pavel Kordik, Miroslav Snorek: Feature Ranking Derived from Data Mining Process. In Artificial Neural Networks - ICANN 2008, 18th International Conference Proceedings vol. nr. , p. , Heidelberg: Springer,, 2008. ISSN BibTex, PDF

    Most common feature ranking methods are based on the sta- tistical approach. This paper compare several statistical methods with new method for feature ranking derived from data mining process. This method ranks features depending on percentage of child units that sur- vived the selection process. A child unit is a processing element trans- forming the parent input features to the output. After training, units are interconnected in the feedforward hybrid neural network called GAME. The selection process is realized by means of niching genetic algorithm, where units connected to least significant features starve and fade from population. Parameters of new feature ranking algorithm are investigated and comparison among different methods is presented on well known real world and artificial data sets.

  • 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


  • Drchal J., Šnorek M.: Diversity visualization in evolutionary algorithms. In: Proceedings of 41th Spring International Conference MOSIS 07, Modelling and Simulation of Systems, p. 77--84, Ostrava: MARQ, 2007. ISBN 978-80-86840-30-7 BibTex, PDF

    Evolutionary Algorithms (EAs) are well-known nature-inspired optimization methods. Diversity is an essenial aspect of each EA. It describes the variability of organisms in population. The lack of diversity is common problem - diversity should be preserved in order to evade local extremes (premature convergence). Niching algorithms are modifications of classical EAs. Niching is based on dividing the population into separate subpopulations - it spreads the organisms effectively all over the search space and hence making the overall population diverse. Using niching methods also requires setting of their parameters, which can be very difficult. This paper presents a novel way of diversity visualization based on physical system simulation. This visualization is helpful when designing and tuning niching algorithms but it has also other uses. The visualization will be presented on NEAT - the evolutionary algorithm which optimizes both the topology and the parameters of neural networks.

  • 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.

  • Pavel Kordík, Oleg Kovářík, Miroslav Šnorek: Optimization of Models: Looking for the Best Strategy. In: Proceedings of 6th EUROSIM Congress on Modelling and Simulation, , Ljubjana, 2007. ISBN 3-901608-32-X BibTex, PDF

    When parameters of model are being adjusted, model is learning to mimic the behaviour of a real world system. Optimization methods are responsible for parameters adjustment. The problem is that each real world system is different and its model should be of different complexity. It is almost impossible to decide which optimization method will perform the best (optimally adjust parameters of the model). In this paper we compare the performance of several methods for nonlinear parameters optimization. The gradient based methods such as Quasi-Newton or Conjugate Gradient are compared to several nature inspired methods. We designed an evolutionary algorithm selecting the best optimization methods for models of various complexity. Our experiments proved that the evolution of optimization methods for particular problems is very promising approach.

  • Aleš Pilný, Pavel Kordík: Reconstruction of Eye Movements Signal using Inductive Model Detecting Saccades. vol. 1 nr. , p. , Czech Technical University, 2007. ISSN BibTex, PDF

    This article describes a method for reconstruction of eye movement signals interfered with saccades and post-determination of inherent frequencies in the signal. For healthy patients, a signal of their eye movements should contain the same frequencies as movements generated by special rotating chair. To determine frequencies in eye movements, saccades have to be removed first. This is not an easy task, because saccades can have various shapes. To detect saccades, we use inductive models trained on various saccadic eye movement signals. To remove saccades and to reconstruct the eye movement signal we wrote special script replacing saccades with estimated trend of signal based on the output of the inductive model. When the reconstructed signal is transformed to the frequency domain, it is easy to decide, whether the eye movements signal contains the same frequencies as the original signal of the rotating chair.

  • Pavel Kordik: Regularization of Evolving Polynomial Models. In: Proceeding of Internation Workshop on Inductive Modelling (IWIM 2007), , 2007. ISBN ISBN 978-80-01-03881-9 BibTex, PDF
  • 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.

  • Drchal J.: Evolution of Recurrent Neural Networks. At: Czech Technical University in Prague, 2006 BibTex, PDF

    This diploma thesis deals with NEAT (NeuroEvolution Of Augmenting Topologies) - it is a state of the art evolutionary system for optimizing topology and parameters of recurrent neural networks. This area of research attracts considerable interest at present. In order to experiment with the algorithm, system is implemented in Java programming language. Then experiments to reproduce previously published results are performed. Work continues with the proposal of a modified system DC NEAT which is then compared to original NEAT. 2-D and 3-D visualizations of recurrent neural networks are proposed and implemented.

  • Kordik P., Saidl J., Snorek M.: Evolutionary Search for Interesting Behavior of Neural Network Ensembles. In: 2006 IEEE Congress on Evolutionary Computation, p. 235-238, Los Alamitos: IEEE Computer Society, 2006. ISBN 0-7803-9489-5 BibTex, PDF
  • P. Kord'{i}k: Fully Automated Knowledge Extraction using Group of Adaptive Models Evolution. At: , Czech Technical University in Prague, FEE, Dep. of Comp. Sci. and Computers, 2006 BibTex, PDF

    Keywords like data mining (DM) and knowledge discovery (KD) appear in several thousands of articles in recent time. Such popularity is driven mainly by demand of private companies. They need to analyze their data effectively to get some new useful knowledge that can be capitalized. This process is called knowledge discovery and data mining is a crucial part of it. Although several methods and algorithms for data mining has been developed, there is still a lot of gaps to fill. The problem is that real world data are so diverse that no universal algorithm has been developed to mine all data effectively. Also stages of the knowledge discovery process need the full time assistance of an expert on data preprocessing, data mining and the knowledge extraction. These problems can be solved by a KD environment capable of automatical data preprocessing, generating regressive, predictive models and classifiers, automatical identification of interesting relationships in data (even in complex and high-dimensional ones) and presenting discovered knowledge in a comprehensible form. In order to develop such environment, this thesis focuses on the research of methods in the areas of data preprocessing, data mining and information visualization. The Group of Adaptive Models Evolution (GAME) is data mining engine able to adapt itself and perform optimally on big (but still limited) group of realworld data sets. The Fully Automated Knowledge Extraction using GAME (FAKE GAME) framework is proposed to automate the KD process and to eliminate the need for the assistance of data mining expert. The GAME engine is the only GMDH type algorithm capable of solving very complex problems (as demonstrated on the Spiral data benchmarking problem). It can handle irrelevant inputs, short and noisy data samples. It uses an evolutionary algorithm to find optimal topology of models. Ensemble techniques are employed to estimate quality and credibility of GAME models. Within the FAKE framework we designed and implemented several modules for data preprocessing, knowledge extraction and for visual knowledge discovery.

  • Drchal J., Šnorek M., Kordík P.: Maintaining Diversity in Population of Evolved Models. In: Proceedings of 40th Spring International Conference MOSIS 06, Modelling and Simulation of Systems, Ostrava: MARQ, 2006. ISBN 80-86840-21-2 BibTex, PDF

    This paper deals with creation of models by means of evolutionary algorithms, particularly with maintaining diversity of population using niching methods. Niching algorithms are known for their ability to search for more optima simultaneously. This is done by splitting the population of models into separate species. Species protect promising but yet not fully developed models. Search for more optima at the same time helps to avoid a premature convergence and therefore deals effectively with local optima. Efficiency of two different niching methods is compared on NEAT applied to the neuro-evolution of models.

  • Buk, Z., Šnorek, M.: Processing the Time Context Based Data Using Soft Computing Methods in Mathematica. In: 5th International Conference APLIMAT, Bratislava: Slovak University of Technology, February 2006. ISBN 80-967305-4-1 BibTex
  • Marek R., Skrbek M.: Remote Access to Hardware Simulation of Neural Networks. In: Proceedings of 40th Spring International Conference MOSIS 06, Modelling and Simulation of Systems, p. 107-112, Ostrava: MARQ, 2006. ISBN 80-86840-21-2 BibTex
  • 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.

  • Skripal P.: The analysis of vocal communication in Parrots. At: Czech Technical University in Prague, 2006 BibTex, PDF

    Phonic expression has always been the primary mean of communication not only for human beings, but also for animals. It constitutes an essential element of their mutual communication. Latest studies of songbirds' social behavior make it apparent that there are many parallels between the evolution of birds' natural vocalization and that of human speech. Besides imitation of words (those of human beings) by itself, it is their natural phonic expression that is of an overriding importance. This way of expression can potentially contain even linguistic structures and thus reflect some of the linguistic expression general features - that of a speech. We can identify this phenomenon also in case of parrots, which are generally known for their highly developed ability of imitation. "Parrot natural speech" phenomenon is thus related not only to profound philosophical implications, but is closely connected to natural sciences and humanities such as ethology and linguistics, too. Outside of this humanities and scientific context can this issue be also viewed upon from the specifically technical point of view. In order to study this phenomenon in depth, one needs to classify parrot phonic expression, which on its lowest level requires for its functioning a system that would be able to analyze the acoustic signal. With help of computing would such a system be able to classify the phonic expression into individual characteristic categories. From the above mentioned phenomenon's point of view it seems that the most interesting approach is their linguistic rating similar to the one being widely used in systems for human speech recognition. The categories themselves can obtain their meaning on several levels. Topic of this final thesis is in addition to the parrot vocalization analyses itself the proposal for implementation of a system that would use its analytical aspect for the need of phonetics expression classification. In this analytical part we shall further on deal with cepstral and statistical analyses of the real phonic samples and will propose a method for an extraction of the appropriate acoustic signal features. The second final part of the thesis is focused on detailed analyses of the self-organizing neural network and its application during the process of the acquired features classification. Implementation of the above mentioned classification system and its testing with real data constitutes an integral part of this study.

  • Skripal P.: The analysis of vocal communication in Parrots. In: Proceedings ACM Student Research Competition 2006, CZ ACM, 2006. ISBN BibTex, PDF

    The topic of the thesis is the analysis of the acoustic communication and vocalization in parrots. In the experimental part of this work, we are dealing with cepstral and statistical analyses of real phonic samples and we will introduce a method for the extraction of appropriate acoustic signal features. The document describes a proposal for implementation of a system that would use the analytical outcomes of our work for the need of phonetics expression classification. We focus on detailed analyses of the self-organizing neural network and its application during the process of the acquired features classification. An overview of implementation of the above-mentioned classification system and of its use with real data constitutes an integral part of this study. Finally in this paper, we will discuss the possibilities of application of the Parrot Speech Toolbox and briefly present some crucial results as the outcomes of the whole work.


  • Mikšíček L., Brachtl M., Buk Z.: CIFS Driver for Palm OS Platform. In: MoWeIT 2005 - Mobile Computing Meets Knowledge Management, p. 87-90, Praha: Česká informatická společnost, 2005. ISBN ISBN 80-903198-0-7 BibTex

    Common Internet File System (CIFS) formerly know as SMB protocol is the most popular protocol for file sharing over the Internet. Originally invented by Microsoft it is the core protocol for Windows file and printer sharing. Implementing CIFS in form of file system driver makes it possible for PDA user to connect to any Windows (or SAMBA) shared disc he has right to access. After being mounted to the Palm OS the shared disc may be used by any Palm OS application which is able to read or write to a memory card. Since the file paradigm is currently the most popular way to operate user data. The CIFS driver for Palm OS improves greatly PDA usability. Users do not need to decide what data they will need outdoors before they leave their office. Remote file access provides for better flexibility of PDA usage.

  • Vladimír Klimeš: Grafické uživatelské rozhraní pro simulaci neuronových sítí. At: Czech Technical University in Prague, 2005 BibTex, PDF
  • Tomáš Horyl: Implementace simulátoru neuronových sítí. At: Czech Technical University in Prague, 2005 BibTex, PDF
  • 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.

  • Buk, Z., Šnorek, M., Skrbek, M.: Simulating the Finite State Machines using Fullly Recurrent Neural Network. In: Proceedings of XXVII-th International Autumn Colloquium ASIS 2005, p. 199-204, Ostrava: MARQ, September 2005. ISBN 80-86840-16-6 BibTex

    In contrast to classic feed-forward neural networks, the recurrent neural networks have an ability to process the time context of input data. Just because of this memory-feature the recurrent neural networks seem to be a powerful instrument for processing the time series, the natural language processing, etc. In this paper we present the ability of a fully recurrent type of neural network to simulate the finite state machines and the technique of automata description extraction from such a network.


  • 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.

  • Skřipal P., and Honkela T.: Framework for Modeling Emotions in Communities of Agents. In: Symposium Proceedings of the 11th Finnish Artificial Intelligence Conference, Life, Cognition and Systems Sciences, September 2004. ISBN BibTex, PDF

    This paper describes a framework for modeling emotions within cognitive agents as an extention to an earlier SOMAgent model of communication and language learning, information fusion and emergent semantic memories. Emotion is considered as a continuous mechanism for flexible adaptation and it is captured through the emergence in an agent’s reaction-emotional memory. In addition to the elementary framework of architecture modifications, in this paper a behavioral model with two pass processing is presented.

  • 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
  • Kučerová A., Drchal J., Němeček J., Lepš M.: Optimizing of Neural Networks Using a Genetic Algorithm. In: Proceedings of WORKSHOP 2003, p. 316-317, Czech Technical University in Prague, 2003. ISBN 80-01-02708-2 BibTex
  • Skrbek, M.: Signature Dynamics on a Mobile Electronic Signature Platform. In: Proceedings of Informatik 2003 Conference, p. 329-332, , 2003. ISBN 3-88579-365-2 BibTex
  • Drchal J., Kučerová A., Němeček J.: Using a Genetic Algorithm for Optimizing Synaptic Weights of Neural Networks. CTU Report vol. 1 nr. 7, p. 161-172, , 2003. ISSN BibTex, PDF

    This paper describes how the SADE genetic algorithm, we developed, could be used for training neural networks. We first make a comparison of the SADE with the traditional backpropagation method and then we demonstrate one of its applications in civil engineering.


  • Drchal J., Kučerová A.: On Using Evolutionary Computational Methods for Layered Neural Network Training. In: Proceedings of the 6th International Student Conference on Electrical Engineering, POSTER 2002, , 2002. ISBN BibTex
  • Drchal J., Kučerová A., Němeček J.: Optimizing Synaptic Weights of Neural Networks. In: Proceedings of the Third International Conference on Engineering Computational Technology, Civil-Comp Press, Stirling, United Kingdom, 2002. ISBN BibTex
  • 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


  • Skrbek, M.: Fast Neural Network Implementation. Neural Network World vol. 9 nr. 5, p. 375-391, IDG Company, 1999. ISSN 1210-0552 BibTex, PDF
  • Skrbek, M., Snorek, M.: SHIFT-ADD Neural Architecture. In: Proceeding of ICECS'99, p. 411-414, , Cyprus, 1999. ISBN 0-7803-5682-9 BibTex