Počet záznamů: 1
On Open Problems Associated with Conditioning in the Dempster-Shafer Belief Function Theory
- 1.
SYSNO ASEP 0576517 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV O - Ostatní Název On Open Problems Associated with Conditioning in the Dempster-Shafer Belief Function Theory Tvůrce(i) Jiroušek, Radim (UTIA-B) ORCID
Kratochvíl, Václav (UTIA-B) RID, ORCID
Shenoy, P. P. (US)Celkový počet autorů 3 Zdroj.dok. Proceedings of the 23rd Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty. - Osaka, Japan : Osaka Metropolitan University, 2023 / Yoshifumi Kusunoki ; Václav Kratochvíl ; Masahiro Inuiguchi ; Ondřej Čepek Rozsah stran s. 1-10 Poč.str. 10 s. Forma vydání Online - E Akce Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty 20232 /23./ Datum konání 16.09.2023 - 20.09.2023 Místo konání Matsuyama Země JP - Japonsko Typ akce WRD Jazyk dok. eng - angličtina Země vyd. JP - Japonsko Klíč. slova belief functions ; conditioning ; composition ; conditional independence Vědní obor RIV BA - Obecná matematika Obor OECD Statistics and probability CEP GA21-07494S GA ČR - Grantová agentura ČR Institucionální podpora UTIA-B - RVO:67985556 Anotace As in probability theory, graphical and compositional models in the Dempster-Shafer (D-S) belief function theory handle multidimensional belief functions applied to support inference for practical problems. Both types of models represent multidimensional belief functions using their low-dimensional marginals. In the case of graphical models, these marginals are usually conditionals, for compositional models, they are unconditional. Nevertheless, one must introduce some conditioning to compose unconditional belief functions and avoid double-counting knowledge. Thus, conditioning is crucial in processing multidimensional compositional models for belief functions.
This paper summarizes some important open problems, the solution of which should enable a trouble-free design of computational processes employing D-S belief functions in AI. For some of them, we discuss possible solutions. The problems considered in this paper are of two types. There are still some gaps that should be filled to get a mathematically consistent uncertainty theory. Other problems concern the computational tractability of procedures arising from the super-exponential growth of the space and time complexity of the designed algorithms.Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2024
Počet záznamů: 1