Jun. 13 2006 2:00PM

Jun. 13 2006 3:00PM

Exploitation of prior knowledge in parameter estimation is vital whenever data are not informative enough or wild transients in the initial estimation phase are practically unacceptable. Both these cases are frequent in applications. Elicitation and quantification prior knowledge is a well elaborated art in societal and medical but not in technical applications. Moreover, the use of an `elicitation expert' is often excluded either due expert's high costs or due to the high complexity of modeled relationships that cannot be grasped by human beings. Thus, an algorithmic support is needed. We exploit to this purpose a recent progress in the methodology of knowledge sharing, achieved in connection with multiple-participant decision-making (DM).

Pravidelný seminář Rozhodování a řízení za neurčitosti. (Contact person: Miroslav Kárný)