0410327 20240103182206.320060210235959.9 3-906454-22-3 Wetaskiwin ICSC 2000 7 s. 528-534BotheH.RojasR. cav_un_auth*0101091 Grim Jiří UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101182 Pudil Pavel UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101197 Somol Petr UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/historie/grim-recognition of handwritten numerals by structural probabilistic neural networks.pdf 12B 09H 06D IAA2075703 GA AV CZ cav_un_auth*0218731 GA402/97/1242 GA ČR cav_un_auth*0009144 VS96063 MŠMT CZ cav_un_auth*0025066 AV0Z1075907 The well known "beauty defect" of probabilistic neural networks is the biologically unnatural complete interconnection of neurons. Despite of deep reasons of this undesirable property, it can be removed by a special subspace approach without leaving the exact framework of Bayesian decision-making. The structural optimization based on EM algorithm is controlled by an infor- mation criterion. In the present paper the method has been applied to recognize unconstrained handwritten numerals. cav_un_auth*0212641 NC 2000 Berlin DE 23.05.2000-26.05.2000 BB RO http://hdl.handle.net/11104/0130418 UTIA-B 20000043 2000 2000 Wetaskiwin ICSC 3-906454-22-3 Proceedings of the Second ICSC Symposium on Neural Computation 528 534 Bothe H. 340 Rojas R. 340