Generalised Weighting: A generic combining form for similarity metrics

In Case-Based Reasoning and in Machine Learning, an important concept is the similarity metric (or measure), a function which rates how similar two objects are, according to some criteria. We concentrate here on case-base queries – finding a case in a case-base which most resembles some probe case. Selecting what metrics are most appropriate is a key part of both designing, and using, a case-base.