Apr. 11 2006 2:00PM

Apr. 11 2006 3:00PM

Bayesian estimation is a standard paradigm of learning that fits well to a subsequent decision making. Never ending controversy between it and Fisherian formulation of statistics and its known restrictions make useful a periodic way back to its basis. In this talk, an attempt is made in this respect. It may serve as
- an outline of a possible set of assumptions hidden behind the use of Bayesian estimation
- a description of very basic Bayesian tools - sketch of main open learning problems

Warning: the talk is given by an engineer so that no mathematical rigor can be expected.

Pravidelný seminář Rozhodování a řízení za neurčitosti. (Kontaktní osoba: Miroslav Kárný)