"1"^^ . . "58"^^ . "2015-05-22+02:00"^^ . . . . "58"^^ . . "Projekt se zab\u00FDval z\u00E1kladn\u00EDm v\u00FDzkumem metod pro data s bohatou strukturou, zejm\u00E9na pokro\u010Dil\u00FDch metod struktur\u00E1ln\u00EDho rozpozn\u00E1v\u00E1n\u00ED vzor\u016F, um\u011Bl\u00FDch neuronov\u00FDch s\u00EDt\u00ED a automat\u016F. Dosa\u017Een\u00E9 v\u00FDsledky jsou pou\u017Eiteln\u00E9 v po\u010D\u00EDta\u010Dov\u00E9m vid\u011Bn\u00ED, zpracov\u00E1n\u00ED p\u0159irozen\u00E9ho jazyka a dob\u00FDv\u00E1n\u00ED znalost\u00ED. V\u00FDsledky byly publikov\u00E1ny v knize a v\u00EDce ne\u017E 50 odborn\u00FDch \u010Dl\u00E1nc\u00EDch, v\u010Detn\u011B 7 \u010Dl\u00E1nk\u016F v impaktovan\u00FDch \u010Dasopisech."@cs . . "Structure and its impact for recognition"@en . . "0"^^ . "The project performed basic research into methods for data with rich structure, in particular advanced methods of structural pattern recognition, artificial neural networks and automata. The obtained results can be used in computer vision, natural language processing, and data mining. They were published in a book and more than 50 research papers, including 7 in journals with impact factor."@en . . . "Struktura a jej\u00ED vyu\u017Eit\u00ED p\u0159i rozpozn\u00E1v\u00E1n\u00ED" . . . . "recognition neural networks restarting automata"@en . "2014-05-02+02:00"^^ . . . "Current trends in information technology show the necessity to develop much more efficient methods for structural data analysis and data mining. At the same time, these directions open new perspectives for further developments in computer science. There we see the opportunity to capitalize on the experience of the team in the field of neural networks and restarting automata. Several types of problems from the area of structural pattern recognition and data mining are namely of a similar character and the principles of learning from examples using neural networks or restarting automata can be used to approach their solution. Our goals are:Design new methods for efficient knowledge extraction. Extend these methods to extract also the information concerning the (hierarchical) structure of the data (using self-organization and sensitivity analysis in BP-networks).Extend the original 1D model of restarting automata to work also on 2D-inputs, e.g. pictures. Analyze theoretical properties of 2D-restarting automata, and 2D-grammars, respectively.Implement the developed methods and test them with the aim to assess their limits in practical applications. Use the developed software modules in two pilot studies \u2013 for knowledge extraction (e.g. from economic or multimedia data) and in structural recognition of mathematical formulae."@en . . "2014-12-31+01:00"^^ . . . "Sou\u010Dasn\u00FD\u00A0trend ve v\u00FDvoji informa\u010Dn\u00EDch technologi\u00ED\u00A0vy\u017Eaduje n\u00E1vrh mnohem efektivn\u011Bj\u0161\u00EDch metod pro struktur\u00E1ln\u00ED anal\u00FDzu dat a dob\u00FDv\u00E1n\u00ED znalost\u00ED. Tyto sm\u011Bry z\u00E1rove\u0148 otev\u00EDraj\u00ED nov\u00E9 perspektivy pro dal\u0161\u00ED rozvoj po\u010D\u00EDta\u010Dov\u00FDch v\u011Bd. Zde vid\u00EDme p\u0159\u00EDle\u017Eitost vyu\u017E\u00EDt zku\u0161enost\u00ED t\u00FDmu v oboru neuronov\u00FDch s\u00EDt\u00ED a restartovac\u00EDch automat\u016F. N\u011Bkter\u00E9 typy \u00FAloh z oblasti rozpozn\u00E1v\u00E1n\u00ED anebo dob\u00FDv\u00E1n\u00ED znalost\u00ED toti\u017E maj\u00ED podobn\u00FD charakter a p\u0159i jejich \u0159e\u0161en\u00ED z\u0159ejm\u011B lze aplikovat principy u\u010Den\u00ED z p\u0159\u00EDklad\u016F s vyu\u017Eit\u00EDm neuronov\u00FDch s\u00EDt\u00ED, resp. restartovac\u00EDch automat\u016F. C\u00EDlem je:Navrhnout nov\u00E9 metody pro efektivn\u00ED extrakci znalost\u00ED. Roz\u0161\u00ED\u0159it tyto metody pro extrakci informac\u00ED o (hierarchick\u00E9) struktu\u0159e dat (s vyu\u017Eit\u00EDm samoorganizace a citlivostn\u00ED anal\u00FDzy v BP-s\u00EDt\u00EDch).Roz\u0161\u00ED\u0159it z\u00E1kladn\u00ED 1D model restartovac\u00EDch automat\u016F i pro pr\u00E1ci nad 2D-vstupy, nap\u0159. obr\u00E1zky. Prov\u00E9st teoretickou anal\u00FDzu vlastnost\u00ED 2D restartovac\u00EDch automat\u016F, resp. 2D gramatik.Vyvinut\u00E9 metody implementovat a otestovat s c\u00EDlem poznat meze jejich praktick\u00E9 pou\u017Eitelnosti. Softwarov\u00E9 moduly budou vyu\u017Eity ve\u00A0dvou pilotn\u00EDch studi\u00EDch \u2013 p\u0159i dob\u00FDv\u00E1n\u00ED znalost\u00ED (nap\u0159. z ekonomick\u00FDch anebo multimedi\u00E1ln\u00EDch dat) a p\u0159i rozpozn\u00E1v\u00E1n\u00ED obraz\u016F matematick\u00FDch vzorc\u016F." . "GAP103/10/0783" . . "2010-01-01+01:00"^^ . "http://www.isvav.cz/projectDetail.do?rowId=GAP103/10/0783"^^ . "1"^^ .