Aplikace/Elektronický dokument

Více-účastnické rozhodování

2009

BDM is an object oriented library of Bayesian decision making written in C++. Basic elements, such as probability density functions and estimators, are peresented as classes. All numerical operations are written using IT++ library which is a C++ wrapper for BLAS and LAPACK libraries. At present, the library implements wide range of filters including Kalman, particle nad marginalized particle filters) and estimation of mixtures of exponential family models.