bibtype C - Conference Paper (international conference)
ARLID 0410327
utime 20240103182206.3
mtime 20060210235959.9
ISBN 3-906454-22-3
title (primary) (eng) Recognition of handwritten numerals by structural probabilistic neural networks
publisher
place Wetaskiwin
name ICSC
pub_time 2000
specification
page_count 7 s.
serial
title Proceedings of the Second ICSC Symposium on Neural Computation
page_num 528-534
editor
name1 Bothe
name2 H.
editor
name1 Rojas
name2 R.
author (primary)
ARLID cav_un_auth*0101091
name1 Grim
name2 Jiří
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101182
name1 Pudil
name2 Pavel
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101197
name1 Somol
name2 Petr
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/historie/grim-recognition of handwritten numerals by structural probabilistic neural networks.pdf
COSATI 12B
COSATI 09H
COSATI 06D
cas_special
project
project_id IAA2075703
agency GA AV
country CZ
ARLID cav_un_auth*0218731
project
project_id GA402/97/1242
agency GA ČR
ARLID cav_un_auth*0009144
project
project_id VS96063
agency MŠMT
country CZ
ARLID cav_un_auth*0025066
research AV0Z1075907
abstract (eng) 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.
action
ARLID cav_un_auth*0212641
name NC 2000
place Berlin
country DE
dates 23.05.2000-26.05.2000
RIV BB
department RO
permalink http://hdl.handle.net/11104/0130418
ID_orig UTIA-B 20000043
arlyear 2000
mrcbU10 2000
mrcbU10 Wetaskiwin ICSC
mrcbU12 3-906454-22-3
mrcbU63 Proceedings of the Second ICSC Symposium on Neural Computation 528 534
mrcbU67 Bothe H. 340
mrcbU67 Rojas R. 340