| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0452538 |
| utime |
20240103211432.6 |
| mtime |
20160215235959.9 |
| SCOPUS |
84949894891 |
| WOS |
000391072100022 |
| DOI |
10.1007/978-3-319-26393-9_22 |
| title
(primary) (eng) |
Mixtures of Product Components versus Mixtures of Dependence Trees |
| specification |
| page_count |
18 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0453648 |
| ISBN |
978-3-319-26393-9 |
| title
|
Computational Intelligence |
| page_num |
365-382 |
| publisher |
| place |
Cham |
| name |
Springer |
| year |
2016 |
|
|
| keyword |
Product mixtures |
| keyword |
Mixtures of Dependence Trees |
| keyword |
EM algorithm |
| author
(primary) |
| ARLID |
cav_un_auth*0101091 |
| full_dept |
Department of Pattern Recognition |
| share |
80 |
| name1 |
Grim |
| name2 |
Jiří |
| institution |
UTIA-B |
| full_dept (cz) |
Rozpoznávání obrazu |
| full_dept (eng) |
Department of Pattern Recognition |
| department (cz) |
RO |
| department (eng) |
RO |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0021092 |
| share |
20 |
| name1 |
Pudil |
| name2 |
P. |
| country |
CZ |
|
| source |
|
| cas_special |
| project |
| ARLID |
cav_un_auth*0308953 |
| project_id |
GAP403/12/1557 |
| agency |
GA ČR |
| country |
CZ |
|
| project |
| ARLID |
cav_un_auth*0303412 |
| project_id |
GA14-02652S |
| agency |
GA ČR |
| country |
CZ |
|
| abstract
(eng) |
Mixtures of product components assume independence of variables given the index of the component. They can be efficiently estimated from data by means of EM algorithm and have some other useful properties. On the other hand, by considering mixtures of dependence trees, we can explicitly describe the statistical relationship between pairs of variables at the level of individual components and therefore approximation power of the resulting mixture may essentially increase. However, we have found in application to classification of numerals that both models perform comparably and the contribution of dependence-tree structures to the log-likelihood criterion decreases in the course of EM iterations. Thus the optimal estimate of dependence-tree mixture tends to reduce to a simple product mixture model. |
| action |
| ARLID |
cav_un_auth*0324200 |
| name |
IJCCI 2014 - International Joint Conference on Computational Intelligence (Rome/Italy) |
| dates |
22.10.2014-24.10.2014 |
| place |
Rome |
| country |
IT |
|
| RIV |
BD |
| reportyear |
2016 |
| num_of_auth |
2 |
| presentation_type |
PR |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0257056 |
| cooperation |
| ARLID |
cav_un_auth*0324201 |
| name |
Faculty of Management, Prague University of Economics |
| institution |
FMJH VSE, Jindřichův Hradec |
| country |
CZ |
|
| confidential |
S |
| mrcbC86 |
3+4 Proceedings Paper Computer Science Artificial Intelligence |
| arlyear |
2016 |
| mrcbU14 |
84949894891 SCOPUS |
| mrcbU34 |
000391072100022 WOS |
| mrcbU63 |
cav_un_epca*0453648 Computational Intelligence 978-3-319-26393-9 365 382 Cham Springer 2016 Studies in Computational Intelligence 620 |
|