Application of classifier systems in improving response surface based approximations for design optimization

Emergent computing paradigms, such as genetic algorithms and neural network s have found increased use in problems of engineering design. These computa tional tools have been shown to be applicable in providing fast function ap proximations, in identifying causality in numerical data, and in the soluti on of generically difficult design optimization problems characterized by n onconvexities in the design space and the presence of discrete and integer design variables. Another aspect of these computational paradigms that have been lumped under the broad subject category of soft computing, is the dom ain of artificial intelligence, knowledge-based expert systems, and machine learning. The present paper explores the use of a machine learning paradig m, the central building blocks of which are tools, such as genetic algorith ms and neural networks. Such learning systems have received some attention in the field of computer science, where they have been referred to as class ifier systems; the paper discusses the significance of this approach in the problem of constructing high-quality global approximations for subsequent use in design optimization. (C) 2000 Elsevier Science Ltd. All rights reser ved.