"Tento \u010Dl\u00E1nek prezentuje novou metodu pro generov\u00E1n\u00ED Markovova \u0159et\u011Bzce neuronovou s\u00EDt\u00ED. Neuronov\u00E1 s\u00ED\u0165 byla pojmenov\u00E1na Temporal Information Categorizing and Learning Map. Jedn\u00E1 se o zdokonalenou variantu s\u00EDt\u011B Categorizing and Learning Module (CALM). Vylep\u0161en\u00ED zahrnuje z\u00E1m\u011Bnu skal\u00E1rn\u00EDho sou\u010Dinu Euklidovou metrikou. Konstrukce Markovova \u0159et\u011Bzce je umo\u017En\u011Bna n\u00E1hradou vnit\u0159n\u00EDch synaps\u00ED s pevn\u00FDmi v\u00E1hami synapsemi s asociativn\u00EDm u\u010Den\u00EDm. V\u00FDsledky s\u00EDt\u011B pracuj\u00EDc\u00ED s jednoduch\u00FDmi um\u011Bl\u00FDmi daty vykazuj\u00ED slibn\u00E9 v\u00FDsledky. D\u00E1le je p\u0159edstavena technika pro vizualizaci Markovov\u00FDch \u0159et\u011Bzc\u016F."@cs . "Springer-Verlag" . . . "[6980F20765E5]" . "Coimbra" . . . "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."@en . "Neuronov\u00E1 s\u00ED\u0165 generuj\u00EDc\u00ED Markov\u016Fv \u0159et\u011Bzec"@cs . "Categorizing and Learning Module; Hidden Markov Model; neural network; signal processing"@en . "Neuronov\u00E1 s\u00ED\u0165 generuj\u00EDc\u00ED Markov\u016Fv \u0159et\u011Bzec"@cs . . "Neural Network Generating Hidden Markov Chain"@en . "Neural Network Generating Hidden Markov Chain" . "RIV/68407700:21230/05:03108598" . "Z(MSM6840770012)" . . . . "RIV/68407700:21230/05:03108598!RIV08-MSM-21230___" . . "Koutn\u00EDk, Jan" . "518;521" . . "4"^^ . . "Neural Network Generating Hidden Markov Chain" . "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." . . "Neural Network Generating Hidden Markov Chain"@en . "2"^^ . "2"^^ . "Adaptive and Natural Computing Algoritms - Proceedings of the International Conference in Coimbra" . "21230" . . . "Wien" . "\u0160norek, Miroslav" . . "532550" . . . "3-211-24934-6" . . "2005-03-20+01:00"^^ .