DWELLS@G.BBN.COM (Dori Wells) (04/12/88)
BBN Science Development Program AI Seminar Series ADAPTIVE KNOWLEDGE REPRESENTATION: A CONTENT SENSITIVE RECOMBINATION MECHANISM FOR GENETIC ALGORITHMS J. David Schaffer Philips Laboratories North American Philips Corporation Briarcliff Manor, New York BBN Laboratories Inc. 10 Moulton Street Large Conference Room, 2nd Floor 10:30 a.m., Tuesday, April 19, 1988 Abstract: This paper describes ongoing research on content sensitive recombination operators for genetic algorithms. A motivation behind this line of inquiry stems from the observation that biological chromosomes appear to contain special nucleotide sequences whose job is to influence the recombination of the expressible genes. We think of these as punctuation marks telling the recombination operators how to do their job. Furthermore, we assume that the distribution of these marks (part of the representation) in a gene pool is determined by the same survival-of-the-fittest and genetic recombination mechanisms that account for the distribution of the expressible genes (the knowledge). A goal of this project is to devise such mechanisms for genetic algorithms and thereby to link the adaptation of a representation to the adaptation of its contents. We hope to do so in a way that capitalizes on the intrinsically parallel behavior of the traditional genetic algorithm. We anticipate benefits of this for machine learning. We describe one mechanism we have devised and present some empirical evidence that suggests it may be as good as or better than a traditional genetic algorithm across a range of search problems. We attempt to show that its action does successfully adapt the search mechanics to the problem space and provide the beginnings of a theory to explain its good performance. -------