| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0040519 |
| utime |
20240103182652.9 |
| mtime |
20060821235959.9 |
| title
(primary) (eng) |
Marginalization algorithm for compositional models |
| specification |
|
| serial |
| ARLID |
cav_un_epca*0076601 |
| ISBN |
2-84254-112-X |
| title
|
IPMU 2006. Information Processing and Management of Uncertainty in Knowledge-Based Systems |
| page_num |
2300-2307 |
| publisher |
| place |
Paris |
| name |
Editions EDK |
| year |
2006 |
|
| editor |
| name1 |
Bouchon-Meunier |
| name2 |
B. |
|
| editor |
|
|
| title
(cze) |
Marginalizační algoritmus pro kompozicionální modely |
| keyword |
compositional model |
| keyword |
multidimensional distribution |
| keyword |
Bayesian network |
| keyword |
marginalization |
| keyword |
algorithm |
| author
(primary) |
| ARLID |
cav_un_auth*0101118 |
| name1 |
Jiroušek |
| name2 |
Radim |
| institution |
UTIA-B |
| full_dept |
Department of Decision Making Theory |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0216188 |
| name1 |
Kratochvíl |
| name2 |
Václav |
| institution |
UTIA-B |
| full_dept |
Department of Decision Making Theory |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| COSATI |
12A |
| cas_special |
| project |
| project_id |
1M0572 |
| agency |
GA MŠk |
| ARLID |
cav_un_auth*0001814 |
|
| project |
| project_id |
IAA2075302 |
| agency |
GA AV ČR |
| ARLID |
cav_un_auth*0001801 |
|
| research |
CEZ:AV0Z10750506 |
| abstract
(eng) |
The paper deals with a problem of marginalization of multidimensional probability distributions represented by compositional models, more precisely by perfect sequence models. It appears thet the solution is more efficient than any known marginalization process for Bayesian networks. This is because the process takes advantage of the fact that perfect sequence models have some information explicitly encoded, which can be got from Bayesian networks by application of reather computationally expensive procedures. |
| abstract
(cze) |
Článek se zabývá problémem marginalizace mnohodimensionálních distribucí reprezentovaných pomocí tak zvaných prefektních posloupností, tedy speciání podtřídou kompozicionálních modelů. V článku je ukázáno, že algoritmus je efektivnější, než kterýkoliv známý algoritmus pro marginalizaci bayesovských sítí. To je proto, že algoritmus využívá skuečnosti, že modely reprezenované perfektními posloupnostmi obsahují explicitně vyjádřenou informaci, jejíž získání z bayesovské sítě může být algoritmicky náročné. |
| action |
| ARLID |
cav_un_auth*0209125 |
| name |
IPMU 2006 /11./ |
| place |
Paris |
| dates |
02.07.2006-07.07.2006 |
| country |
FR |
|
| reportyear |
2007 |
| RIV |
BA |
| permalink |
http://hdl.handle.net/11104/0134228 |
| arlyear |
2006 |
| mrcbU63 |
cav_un_epca*0076601 IPMU 2006. Information Processing and Management of Uncertainty in Knowledge-Based Systems 2-84254-112-X 2300 2307 Paris Editions EDK 2006 |
| mrcbU67 |
Bouchon-Meunier B. 340 |
| mrcbU67 |
Yager R. R. 340 |
|