Multiple models in intelligent training
Julie‐Ann Sime, R.R. Leitch · International Conference on Intelligent Systems · 1992
As physical systems becomes larger and more complex, it is more and more difficult to model them, and to reason about their behaviour. Multiple models can be used to reduce the complexity of a model to a manageable size. Each model representing a particular aspect of the system. This is done by only modelling features that are relevant to the current task. The paper provides a coherent foundation for the dimensions along which these models vary, within the context of instruction about a physical system. How these models may enhance instruction is discussed. In particular qualitative modelling through cognitive apprenticeship. The modelling dimensions are illustrated through the modelling of an experimental Process Rig, for the purposes of building an intelligent training system. >