From Information to Evidence in a Bayesian Network

摘要: Evidence in a Bayesian network comes from information based on the observation of one or more variables. A review terminology leads to assessment that two main types non-deterministic evidence have been defined, namely likelihood and probabilistic but distinction between fixed not is clear, neither nor concepts clearly defined. In particular, term soft confusing. The article presents definitions related use networks, terms specification propagation. Several examples help understand how an initial piece can be specified as finding network.