"Udr\u017Eov\u00E1n\u00ED diverzity v populac\u00EDch model\u016F vznikl\u00FDch evoluc\u00ED"@cs . "483921" . "Ostrava" . "P\u0159erov" . . "MARQ" . "\u010Cl\u00E1nek pojedn\u00E1v\u00E1 o vytv\u00E1\u0159en\u00ED model\u016F pomoc\u00ED evolu\u010Dn\u00EDch algoritm\u016F, zejm\u00E9na pak o udr\u017Eov\u00E1n\u00ED diverzity v populac\u00EDch s pou\u017Eit\u00EDm metod nichingu. Niching algoritmy jsou zn\u00E1my t\u00EDm, \u017Ee vyhled\u00E1v\u00E1j\u00ED sou\u010Dasn\u011B v\u00EDce optim. Rozd\u011Bluj\u00ED populaci model\u016F do odd\u011Blen\u00FDch druh\u016F. Rozd\u011Blen\u00ED na druhy chr\u00E1n\u00ED slibn\u00E9, ale je\u0161t\u011B nedostate\u010Dn\u011B vyvinut\u00E9 modely. Hled\u00E1n\u00ED v\u00EDce optim sou\u010Dasn\u011B pom\u00E1h\u00E1 \u0159e\u0161it probl\u00E9m p\u0159ed\u010Dasn\u00E9 konvergence, a t\u00EDm br\u00E1n\u00ED uv\u00E1znut\u00ED v lok\u00E1ln\u00EDch optimech. \u010Cl\u00E1nek porovn\u00E1v\u00E1 dv\u011B r\u016Fzn\u00E9 metody nichingu v syst\u00E9mu pro evoluci neuronov\u00FDch s\u00EDt\u00ED NEAT."@cs . . . "2006-04-25+02:00"^^ . "Z(MSM6840770012)" . "Maintaining Diversity in Population of Evolved Models"@en . . "[04E68D799B71]" . "Maintaining Diversity in Population of Evolved Models" . . . . . "RIV/68407700:21230/06:03128798!RIV07-MSM-21230___" . . "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."@en . . . "RIV/68407700:21230/06:03128798" . "113 ; 120" . "Maintaining Diversity in Population of Evolved Models" . "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." . . . "NEAT; diversity; evolutionary algorithms; niching algorithms; recurrent neural networks"@en . . "3"^^ . . . "Proceedings of 40th Spring International Conference MOSIS 06, Modelling and Simulation of Systems" . "Udr\u017Eov\u00E1n\u00ED diverzity v populac\u00EDch model\u016F vznikl\u00FDch evoluc\u00ED"@cs . "80-86840-21-2" . "3"^^ . . "21230" . "8"^^ . "Maintaining Diversity in Population of Evolved Models"@en . "Drchal, Jan" . . . "\u0160norek, Miroslav" . "Kord\u00EDk, Pavel" . .