The Role of Prior Causal Theories in Generalization

OCCAM is a program which organizes memories of CvenB and learns by creating generalizations describing the reasons for the oumomes of the event% OCCAM integrates two sources of information when forming a ge”eBJiZatioIl: l Correlational information which meals perceived regularities in We”% l Prior causal theories which explain regularities in eyents The former has been extensively studied in machine learning. Recently, there has been interest in explanation-based learning in which the latter source of information is utilized. In CXCAM, prior causal theories am preferred to correlational information when forming generalizations. This strategy is supported by P number of empirical investigations. Generalization rules are used to suggest causal and intendanal relational relationships. In familiar domains, these nlaticmships are confiid or denied by prior causal theories which differentiate the relevant and irrelevant features. In unfamiliar domains. lbe poslulated causal and intentional relationships serve as a basis fm the ccmsrmction of causal theories.