Počet záznamů: 1
Measuring Quality of Belief Function Approximations
- 1.0555172 - ÚTIA 2023 RIV CH eng C - Konferenční příspěvek (zahraniční konf.)
Jiroušek, Radim - Kratochvíl, Václav
Measuring Quality of Belief Function Approximations.
Integrated Uncertainty in Knowledge Modelling and Decision Making. Cham: Springer, 2022 - (Honda, K.; Entani, T.; Ubukata, S.; Huynh, V.; Inuiguchi, M.), s. 3-15, č. článku 1. Lecture Notes in Computer Science, 13199. ISBN 978-3-030-98017-7. ISSN 0302-9743. E-ISSN 1611-3349.
[International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making 2022 /9./. Ishikawa (JP), 18.03.2022-19.03.2022]
Grant ostatní: GA ČR(CZ) GA19-06569S
Program: GA
Institucionální podpora: RVO:67985556
Klíčová slova: Belief functions * Divergence * Approximation * Compositional models
Obor OECD: Pure mathematics
http://library.utia.cas.cz/separaty/2022/MTR/jirousek-0555172.pdf
Because of the high computational complexity of the respective procedures, the application of belief-function theory to problems of practice is possible only when the considered belief functions are approximated in an efficient way. Not all measures of similarity/dissimilarity are felicitous to measure the quality of such approximations. The paper presents results from a pilot study that tries to detect the divergences suitable for this purpose.
Trvalý link: http://hdl.handle.net/11104/0330288
Počet záznamů: 1