BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Hông Vân Lê (Institute of Mathematics of ASCR) DTSTART:20251217T123000Z DTEND:20251217T133000Z DTSTAMP:20260418T095039Z UID:PHK-cohomology-seminar/145 DESCRIPTION:Title: Probabilistic morphisms\, stochastic processes\, and Baye sian supervised learning\nby Hông Vân Lê (Institute of Mathematics of ASCR) as part of Prague-Hradec Kralove seminar Cohomology in algebra\, geometry\, physics and statistics\n\nLecture held in the blue lecture room + ZOOM meeting.\n\nAbstract\nUsing a categorical approach to Markov kerne ls\, and stochastic processes taking values in the space of probability me asures on a label space\, I propose a unifying model for Bayesian supervis ed learning. I show that batch learning equals online learning in Bayes ian supervised learning. As a result\, I derive a recursive formula for pr edictive distributions which reduces to the Kalman filter in Gaussian proc ess regression. Finally\, I shall discuss some related problems in mathema tical machine learning.\n LOCATION:https://researchseminars.org/talk/PHK-cohomology-seminar/145/ END:VEVENT END:VCALENDAR