On the design of supra-classifiers for knowledge reuse

We (1997) have introduced a framework for the reuse of knowledge from previously trained classifiers to improve performance in a current, possibly related classification task. This framework requires the use of a supra-classifier, which makes a classification decision based on the outputs of a large number of previously trained diverse classifiers. We discuss the performance requirements of a good supra-classifier and introduce several possible supra-classifier architectures. We make performance comparisons of these architectures using public domain data sets for the problem of inadequate training data and compare their scalability in the number of simultaneously reused classifiers