2008 | OriginalPaper | Buchkapitel
Evolvable Hardware: A Problem of Generalization Which Works Best: Large Population Size and Small Number of Generations or visa versa?
verfasst von : Elhadj Benkhelifa, Anthony Pipe, Mokhtar Nibouche, Gabriel Dragffy
Erschienen in: Nature Inspired Cooperative Strategies for Optimization (NICSO 2007)
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Evolutionary Algorithms (EAs), emulate, in several different applications, the Darwinian Evolution Theory, which advocates the adaptation of living beings to their environment and the survival of the fittest individual through natural selection. Indeed, since the 1990s, EAs have emerged as unconventional method to automatically design and optimise digital circuitry. Researchers in this field have adopted
Evolvable Hardware
(EHW) to refer to a reconfigurable digital system that can evolve to behave as desired. One difficult task in EHW is choosing the right EA’s parameters such as the population size, number of evaluations (generations), genetic operators (mutation, crossover), selection method and so on. This paper is part of the Evolvable Embryonics project and is particularly interested in the former two forces of the EA, population size and number of generations.