ABSTRACT Classifier systems are massively parallel, message-passing, rule-based systems that learn through credit assignment (the bucket brigade algorithm) and rule discovery (the genetic algorithm). They typically operate in environments that exhibit one or more of the following characteristics: (1) perpetually novel events accompanied by large amounts of noisy or irrelevant data; (2) continual, often real-time, requirements for action; (3) implicitly or inexactly defined goals; and (4) sparse payoff or reinforcement obtainable only through long action sequences. Classifier systems are designed to absorb new information continuously from such environments, devising sets of compet- ing hypotheses (expressed as rules) without disturbing significantly capabilities already acquired. This paper reviews the definition, theory, and extant applications of classifier systems, comparing them with other machine learning techniques, and closing with a discussion of advantages, problems, and possible extensions of classifier systems. Artificial Intelligence, 40 (1-3), 235-82.

"In propositional logic (zero order) a system of logical rules may be put under the form of a conjunction of disjunction, i.e. a “satisfiability” or SAT-problem. SAT is central to NP-complete problems. Any result obtained on SAT would have consequences for a lot of problems important in artificial intelligence. We deal with the question of the number N of solutions of SAT. Firstly, any system of SAT clauses may be transformed in a system of independent clauses by an exponential process; N may be computed exactly. Secondly, by a statistical approach, results are obtained showing that for a given SAT-instance, it should be possible to find an estimate of N with a margin of confidence in polynomial time. Thirdly, we demonstrate the usefulness of these ideas on large knowledge bases." Int. J. Patt. Recogn. Artif. Intell. 03, 53 (1989).

Proc. Eleventh Intl. Joint Conference on Artificial Intelligence (pp. 681-687). Detroit, MI: IJCAII.

We built on previous work to develop an evaluation method that can be used to select expert system applications which are most likely to be successfully implemented. Both essential and desirable features of an expert system application are discussed. Essential features are used to ensure that the application does not require technology beyond the state of the art. Advice on helpful directions for evaluating candidate expert system applications is also given.

A novel approach is presented for the development of expert systems for structural design problems. This approach differs from the conventional expert systems in two fundamental respects. As an example of this approach, a prototype coupled expert system, the bridge truss expert (BTExpert), is presented for optimum design of bridge trusses subjected to moving loads. BTExpert was developed by interfacing an interactive optimization program developed in Fortran 77 to an expert system shell developed in Pascal.

Evaluation should be a mechanism of progress both within and across AI research projects. For the individual, evaluation can tell us how and why our methods and programs work and, so, tell us how our research should proceed. For the community, evaluation expedites the understanding of available methods and, so, their integration into further research. In this article, we present a five-stage model of AI research and describe guidelines for evaluation that are appropriate for each stage. These guidelines, in the form of evaluation criteria and techniques, suggest how to perform evaluation. We conclude with a set of recommendations that suggest how to encourage the evaluation of AI research.

He is a and Information Science at The and Information Science at The Distinguished Professor of Computer Ohio State University, Columbus, Ohio State University, Columbus, Science at the University of Minnesota, Ohio 43210. He is currently writing Ohio 43210. He is currently writing a position he has held since 1984.

AAAI is a society devoted to supporting the progress in science, technology and applications of AI. I thought I would use this occasion to share with you some of my thoughts on the recent advances in AI, the insights and theoretical foundations that have emerged out of the past thirty years of stable, sustained, systematic explorations in our field, and the grand challenges motivating the research in our field.

A novel approach is presented for the development of expert systems for structural design problems. This approach differs from the conventional expert systems in two fundamental respects. First, mathematical optimization is introduced into the design process. Second, a computer is used to obtain parts of the knowledge necessary in the expert systems in addition to heuristics and experiential knowledge obtained from documented materials and human experts. As an example of this approach, a prototype coupled expert system, the bridge truss expert (BTExpert), is presented for optimum design of bridge trusses subjected to moving loads. BTExpert was developed by interfacing an interactive optimization program developed in Fortran 77 to an expert system shell developed in Pascal. This new generation of expert systems-embracing various advanced technologies such as AI (machine intelligence), the numeric optimization technique, and interactive computer graphics -- should find enormous practical implications.

A workshop on high-level connectionist models was held in Las Cruces, New Mexico, on 9-11 April 1988 with support from the Association for the Advancement of Artificial Intelligence and the Office of Naval Research. John Barnden and Jordan Pollack organized and hosted the workshop and will edit a book containing the proceedings and commentary. The book will be published by Ablex as the first volume in a series entitled Advances in Connectionist and Neural Computation Theory.