Knowledge interpolation: A simple approach to rapid symbolic reasoning

Abstract

The non-algorithmic nature of traditional knowledge-based (KB) reasoning approaches makes these techniques open-ended. As a result, KB techniques appear unsuitable for real-time applications as is evident from the small number of appearances of KB techniques in real-time domains. The technique of knowledge interpolation is a potential remedy for the shortcoming. Intuitively, the technique imitates the numerical-analysis technique of interpolation, derives solutions for an unknown problem from some already known values, and thereby avoids extensive searches of the knowledge base.  an extra inherent advantage is that it gives the computation a more predictable algorithmic character. Hence not only can a computation's temporal requirements be estimated, but also requirements themselves may be reduced significantly.
Effective application of this technique needs to answer two questions: what are the prerequisites for application of such techniques, and what are the possible ways of application. This paper studies both issues from an implementational point of view.