0476602 20240103214323.020170731235959.9 85025114720 000432996600012 10.1007/978-3-319-61581-3_12 10 s. P cav_un_epca*0476601978-3-319-61580-6125-134ChamSpringer2017AntonucciA.CholvyL.PapiniO. computerized adaptive testing probabilistic graphical models gradient methods cav_un_auth*0329423 Plajner Martin UTIA-B Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101228 Vomlel Jiří UTIA-B Matematická teorie rozhodování Department of Decision Making Theory MTR MTR Department of Decision Making Theory Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2017/MTR/plajner-0476602.pdf cav_un_auth*0332303 GA16-12010S GA ČR CZ Artificial intelligence is present in many modern computer science applications. The question of effectively learning parameters of such models even with small data samples is still very active. It turns out that restricting conditional probabilities of a probabilistic model by monotonicity conditions might be useful in certain situations. Moreover, in some cases, the modeled reality requires these conditions to hold. In this article we focus on monotonicity conditions in Bayesian Network models. We present an algorithm for learning model parameters, which satisfy monotonicity conditions, based on gradient descent optimization. We test the proposed method on two data sets. One set is synthetic and the other is formed by real data collected for computerized adaptive testing. We compare obtained results with the isotonic regression EM method by Masegosa et al. which also learns BN model parameters satisfying monotonicity. A comparison is performed also with the standard unrestricted EM algorithm for BN learning. Obtained experimental results in our experiments clearly justify monotonicity restrictions. As a consequence of monotonicity requirements, resulting models better fit data. cav_un_auth*0348187 ECSQARU: European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty 20170710 20170714 Lugano CH JD 20000 20200 20205 2018 2 RVO:67985556 http://hdl.handle.net/11104/0273648 1 S RIV/67985556:_____/17:00476602!RIV18-AV0-67985556 191975664 Doplnění UT WOS RIV/67985556:_____/17:00476602!RIV18-GA0-67985556 191965015 Doplnění UT WOS n.a. Proceedings Paper Computer Science Artificial Intelligence|Logic n.a. Proceedings Paper Computer Science Artificial Intelligence|Logic n.a. Proceedings Paper Computer Science Artificial Intelligence|Logic 2017 85025114720 SCOPUS PUBMED 000432996600012 WOS cav_un_epca*0476601 Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2017 Springer 2017 Cham 125 134 978-3-319-61580-6 Lecture Notes in Computer Science 10369 340 Antonucci A. 340 Cholvy L. 340 Papini O.