. "1"^^ . . "1211-8516" . . "1"^^ . "1" . "trend; neural net; time series; model; learning of neural net; error function"@en . "11"^^ . "Predik\u010Dn\u00ED modely s neuronov\u00FDmi s\u00EDt\u011Bmi" . "Kone\u010Dn\u00FD, Vladim\u00EDr" . "P\u0159\u00EDsp\u011Bvek je zam\u011B\u0159en na z\u00E1kladn\u00ED probl\u00E9my \u0159e\u0161en\u00ED trend\u016F ekonomick\u00FDch ukazatel\u016F vyu\u017Eit\u00EDm neuronov\u00FDch s\u00EDt\u00ED. Jedn\u00E1 se o volbu modelu a n\u00E1sleden\u011B konfiguraci neuronov\u00E9 s\u00EDt\u011B, v\u00FDpo\u010Detn\u00ED funkci neuron\u016F a u\u010Den\u00ED predikci. P\u0159\u00EDsp\u011Bvek obsahuje dva z\u00E1kladn\u00ED modely, kter\u00E9 vyu\u017E\u00EDvaj\u00ED v\u00EDce\u00FArov\u0148ovou s\u00ED\u0165 a zp\u016Fsob stanoven\u00ED jej\u00ED konfigurace. D\u00E1le je stanoveno jednoduch\u00E9 pravidlo u\u010Den\u00ED s\u00EDt\u011B pro z\u00EDsk\u00E1n\u00ED v\u011Brohodn\u00E9 predikce. Experimenty jsou prov\u00E1d\u011Bny na skute\u010Dn\u00E9 \u010Dasov\u00E9 \u0159ad\u011B v\u00FDvoje kurzu K\u010D/Euro a K\u010D/USD. Hlavn\u00EDm d\u016Fvodem volby t\u011Bchto \u010Dasov\u00FDch \u0159ad je jejich dostupnost pro dostate\u010Dn\u011B dlouh\u00E9 obdob\u00ED. V proveden\u00FDch experimentech jsou ov\u011B\u0159ov\u00E1ny oba uveden\u00E9 druhy predik\u010Dn\u00EDch model\u016F s nej\u010Dast\u011Bji pou\u017E\u00EDvan\u00FDmi druhy v\u00FDpo\u010Detn\u00EDch funkc\u00ED neuron\u016F. Dosa\u017Een\u00E9 v\u00FDsledky predikce jsou prezentov\u00E1ny jak v numerick\u00E9, tak i grafick\u00E9 podob\u011B."@cs . . "[45C4EA0AFD18]" . "P\u0159\u00EDsp\u011Bvek je zam\u011B\u0159en na z\u00E1kladn\u00ED probl\u00E9my \u0159e\u0161en\u00ED trend\u016F ekonomick\u00FDch ukazatel\u016F vyu\u017Eit\u00EDm neuronov\u00FDch s\u00EDt\u00ED. Jedn\u00E1 se o volbu modelu a n\u00E1sleden\u011B konfiguraci neuronov\u00E9 s\u00EDt\u011B, v\u00FDpo\u010Detn\u00ED funkci neuron\u016F a u\u010Den\u00ED predikci. P\u0159\u00EDsp\u011Bvek obsahuje dva z\u00E1kladn\u00ED modely, kter\u00E9 vyu\u017E\u00EDvaj\u00ED v\u00EDce\u00FArov\u0148ovou s\u00ED\u0165 a zp\u016Fsob stanoven\u00ED jej\u00ED konfigurace. D\u00E1le je stanoveno jednoduch\u00E9 pravidlo u\u010Den\u00ED s\u00EDt\u011B pro z\u00EDsk\u00E1n\u00ED v\u011Brohodn\u00E9 predikce. Experimenty jsou prov\u00E1d\u011Bny na skute\u010Dn\u00E9 \u010Dasov\u00E9 \u0159ad\u011B v\u00FDvoje kurzu K\u010D/Euro a K\u010D/USD. Hlavn\u00EDm d\u016Fvodem volby t\u011Bchto \u010Dasov\u00FDch \u0159ad je jejich dostupnost pro dostate\u010Dn\u011B dlouh\u00E9 obdob\u00ED. V proveden\u00FDch experimentech jsou ov\u011B\u0159ov\u00E1ny oba uveden\u00E9 druhy predik\u010Dn\u00EDch model\u016F s nej\u010Dast\u011Bji pou\u017E\u00EDvan\u00FDmi druhy v\u00FDpo\u010Detn\u00EDch funkc\u00ED neuron\u016F. Dosa\u017Een\u00E9 v\u00FDsledky predikce jsou prezentov\u00E1ny jak v numerick\u00E9, tak i grafick\u00E9 podob\u011B." . "CZ - \u010Cesk\u00E1 republika" . "RIV/62156489:43110/08:00113456!RIV09-MSM-43110___" . "RIV/62156489:43110/08:00113456" . "Z(MSM6215648904)" . "Predictions models with neural nets"@en . "LVII" . . . "Predik\u010Dn\u00ED modely s neuronov\u00FDmi s\u00EDt\u011Bmi"@cs . . "Acta Universitatis agriculturae et silviculturae Mendelianae Brunensis : Acta of Mendel University of agriculture and forestry Brno = Acta Mendelovy zem\u011Bd\u011Blsk\u00E9 a lesnick\u00E9 univerzity v Brn\u011B" . . . "Predik\u010Dn\u00ED modely s neuronov\u00FDmi s\u00EDt\u011Bmi"@cs . . . . . "388794" . "The contribution is oriented to basic problems trend's solution of economic pointers, using neural networks. Problems include choice of the suitable model and consequently configuration of neu-ral nets, choice computational function of neurons and the way prediction learning. The contribu-tion contents two basic models that use structure of multiplayer neural nets and way of determi-nation their configuration. It is postulate a simple rule for teaching period of neural net, to get most credible prediction. Experiments are executed with really data evolution of exchange rate K\u010D/Euro and K\u010D/USD. The Main reason choice this time series is their availability for sufficient long period. In carry out of experiments are verify both given basic kind of prediction models with most frequent use functions of neurons. Achieve prediction results are presented as in numerical and so in graphical forms."@en . "Predik\u010Dn\u00ED modely s neuronov\u00FDmi s\u00EDt\u011Bmi" . . . "Predictions models with neural nets"@en . "43110" . . . .