A New Model of Reflective Introspective Learning
Susan H. Fox · 1998
E-maih fox~macalester, edu Systems which introspect about their own processes can improve their reasoning behavior in response to experience using "introspective learning " techniques. Many systems which perform introspective learning an-alyze and change only an underlying domain task’s rea-soning processes. They do not possess the ability to r~ flectively introspect about the introspective task itself. We present a model of a truly reflective introspective learning system which uses the same case-based reason-ing mechanisms for both its domain and introspective tasks. The reuse of case-based reasoning mechanisms enables the reuse of introspective models and mecha-nisms developed for a CBR domain reasoner to reflect about the introspective process itself. We suggest an introspective model capable of reflection, and begin to address the issue of balancing introspection axtd action ~dthin a reflective system.