0499667 20240103221326.420190111235959.9 85056995230 000450651000042 10.1109/MLSP.2018.8517020 6 s. P cav_un_epca*0499864978-1-5386-5478-11551-2541PiscatawayIEEE2018 Bayesian transfer learning Fully probabilistic design Kalman filtering cav_un_auth*0370767 Adaptivní systémy Department of Adaptive Systems AS AS Department of Adaptive Systems 50 Papež Milan UTIA-B CZ K Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0370768 Adaptivní systémy Department of Adaptive Systems AS AS Department of Adaptive Systems 50 Quinn Anthony UTIA-B IE S Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2019/AS/papez-0499667.pdf GA18-15970S GA ČR CZ cav_un_auth*0362986 Transfer learning is a framework that includes---among other topics---the design of knowledge transfer mechanisms between Bayesian filters. Transfer learning strategies in this context typically rely on a complete stochastic dependence structure being specified between the participating learning procedures (filters). This paper proposes a method that does not require such a restrictive assumption. The solution in this incomplete modelling case is based on the fully probabilistic design of an unknown probability distribution which conditions on knowledge in the form of an externally supplied distribution. We are specifically interested in the situation where the external distribution accumulates knowledge dynamically via Kalman filtering. Simulations illustrate that the proposed algorithm outperforms alternative methods for transferring this dynamic knowledge from the external Kalman filter. cav_un_auth*0370769 International Workshop on Machine Learning for Signal Processing 2018 (MLSP 2018) /28./ 20180917 Aalborg DK 20180920 BB 10000 10100 10103 2019 2 PO RVO:67985556 http://hdl.handle.net/11104/0292053 1 cav_un_auth*0345684 Trinity College Dublin, the University of Dublin TCD IE S 8517020 1 Proceedings Paper Computer Science Artificial Intelligence|Computer Science Theory Methods|Engineering Electrical Electronic 2018 85056995230 SCOPUS PUBMED 000450651000042 WOS cav_un_epca*0499864 PROCEEDINGS OF MLSP 2018 : IEEE 28th International Workshop on Machine Learning for Signal Processing 978-1-5386-5478-1 1551-2541 Piscataway IEEE 2018