A Conditional Reflex Model Based Bayesian Network (CRMBBN)

A model based Bayesian network (CRMBBN) is presented with classical conditional behaviors. A new concept about sense is introduced, the model regards sense as input and output sense prediction of next time. Reflex is not involved in CRMBBN, the non-classical conditional reflex is put into the instinctive behavior of the agent. So the model constructs Cause-Effect relationships between classical conditional sense and non-classical conditional sense, and the relationships are presented by Bayesian Network. A serial typical experiments have proved that CRMBBN can successfully stimulate many phenomena such as acquire, inter-stimulus effects, extinction and so on.