0532053 20240103224404.820200908235959.9 85085247688 000540817100003 10.1016/j.sigpro.2020.107624 11 s. P cav_un_epca*02550760165-1684Elsevier Bayesian transfer learning Student-t filtering Incomplete modelling Fully probabilistic design Variational Bayes Robust transfer cav_un_auth*0370767 Papež Milan UTIA-B Adaptivní systémy Department of Adaptive Systems AS AS Department of Adaptive Systems CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0370768 Quinn Anthony UTIA-B Adaptivní systémy Department of Adaptive Systems AS AS Department of Adaptive Systems IE Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2020/AS/papez-0532053.pdf https://www.sciencedirect.com/science/article/pii/S0165168420301675 GA18-15970S GA ČR CZ cav_un_auth*0362986 The problem of sequentially transferring a data-predictive probability distribution from a source to a target Bayesian filter is addressed in this paper. In many practical settings, this transfer is incompletely modelled, since the stochastic dependence structure between the filters typically cannot be fully specified. We therefore adopt fully probabilistic design to select the optimal transfer mechanism. We relax the target observation model via a scale-mixing parameter, which proves vital in successfully transferring the first and second moments of the source data predictor. This sensitivity to the transferred second moment ensures that imprecise predictors are rejected, achieving robust transfer. Indeed, Student-t state and observation models are adopted for both learning processes, in order to handle outliers in all hidden and observed variables. A recursive outlier-robust Bayesian transfer learning algorithm is recovered via a local variational Bayes approximation. The outlier rejection and positive transfer properties of the resulting algorithm are clearly demonstrated in a simulated planar position-velocity system, as is the key property of imprecise knowledge rejection (robust transfer), unavailable in current Bayesian transfer algorithms. Performance comparison with particle filter variants demonstrates the successful convergence of our robust variational Bayes transfer learning algorithm in sequential processing. WOS BB 10000 10200 10201 2021 2 4 A sml 4as 20231122145108.4 RVO:67985556 http://hdl.handle.net/11104/0310668 1 S Publishing Agreement 20200430 107624 3+4 Article Engineering Electrical Electronic C ENGINEERING.ELECTRICAL&ELECTRONIC 4.259 1.523 5.9 0.01736 0.964 15960 170 0.907 40.29 5.1 5616 Q1 4.173 415 Q1 78.831 84.1 Q1 Q2 1.37 Q1 84.066 2020 Soubory v repozitáři: papez-0532053-SIGPRO107624.html 85085247688 SCOPUS PUBMED 000540817100003 WOS cav_un_epca*0255076 Signal Processing 0165-1684 1872-7557 Volume 175 č. 1 2020 Elsevier