bibtype	J - Journal Article
ARLID	0544189
utime	20240103230042.0
mtime	20210801235959.9
WOS	000694711500021
SCOPUS	85111504429
DOI	10.1016/j.patrec.2021.07.011
title (primary) (eng)	On Assigning Probabilities to New Hypotheses
specification	page_count 6 s. media_type P
serial	ARLID cav_un_epca*0257389 ISSN 0167-8655 title Pattern Recognition Letters volume_id 150 volume 1 (2021) page_num 170-175 publisher name Elsevier
keyword	minimum relative-entropy principle
keyword	prior probability
keyword	hypothesis
author (primary)	ARLID cav_un_auth*0101124 name1 Kárný name2 Miroslav institution UTIA-B full_dept (cz) Adaptivní systémy full_dept (eng) Department of Adaptive Systems department (cz) AS department (eng) AS share 100 garant A fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source	url http://library.utia.cas.cz/separaty/2021/AS/karny-0544189.pdf
source	url https://www.sciencedirect.com/science/article/pii/S0167865521002567
cas_special	project project_id LTC18075 agency GA MŠk country CZ ARLID cav_un_auth*0372050 project project_id CA16228 agency The European Cooperation in Science and Technology (COST) country XE ARLID cav_un_auth*0372051 abstract (eng) The paper proposes the way how to assign a proper prior probability to a new, generally compound, hypothesis. To this purpose, it uses the minimum relative-entropy principle\nand a forecaster-based knowledge transfer. Methodologically, it opens a way towards enriching the standard Bayesian framework by the possibility to extend the set of models during learning without the need to restart. The presented use scenarios concern: (a) creating new hypotheses, (b) learning problems with an insuffcient amount of data, and\n(c) sequential Monte Carlo estimation. They indicate a strong application potential of the proposed technique. Related interesting open research problems are listed. result_subspec WOS RIV IN FORD0 10000 FORD1 10200 FORD2 10201 reportyear 2022 num_of_auth 1 mrcbC52 4 A sml 4as 20231122145841.9 inst_support RVO:67985556 permalink http://hdl.handle.net/11104/0321363 confidential S contract name ELSEVIER Publishing Agreement date 20210726 mrcbC86 3+4 Article Computer Science Artificial Intelligence mrcbC91 C mrcbT16-e COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE mrcbT16-f 4.253 mrcbT16-g 1.041 mrcbT16-h 8.4 mrcbT16-i 0.01281 mrcbT16-j 0.804 mrcbT16-k 18442 mrcbT16-q 188 mrcbT16-s 1.479 mrcbT16-y 33.16 mrcbT16-x 5.74 mrcbT16-3 6461 mrcbT16-4 Q1 mrcbT16-5 4.502 mrcbT16-6 364 mrcbT16-7 Q2 mrcbT16-C 63.8 mrcbT16-D Q3 mrcbT16-E Q2 mrcbT16-M 0.91 mrcbT16-N Q2 mrcbT16-P 63.793 arlyear 2021 mrcbTft \nSoubory v repozitáři: karny-0544189-PATREC8308.html mrcbU14 85111504429 SCOPUS mrcbU24 PUBMED mrcbU34 000694711500021 WOS mrcbU63 cav_un_epca*0257389 Pattern Recognition Letters 0167-8655 1872-7344 Roč. 150 č. 1 2021 170 175 Elsevier