The multi-purpose incremental learning system AQ15 and its testing application to three medical domains

The demonstration that by applying the proposed method of cover truncation and analogical matching, called TRUNC, one may drastically decrease the complexity of the knowledge base without affecting its performance accuracy is demonstrated.

Abstract

AQ15 is a multi-purpose inductive learning system that uses logic-based, user-oriented knowledge representation, is able to incrementally learn disjunctive concepts from noisy or overlapping examples, and can perform constructive induction (i.e., can generate new attributes in the process of learning). In an experimental application to three medical domains, the program learned decision rules that performed at the level of accuracy of human experts. A surprising and potentially significant result is the demonstration that by applying the proposed method of cover truncation and analogical matching, called TRUNC, one may drastically decrease the complexity of the knowledge base without affecting its performance accuracy.