Abstract
As I have formulated the problem, the only information about a function available to a search strategy at the outset is the dimensionality of the space. During a search, a hypothetical perfect strategy would quickly deduce the structure of the landscape, and adapt its behavior to find a solution state rapidly. To estimate how close any real search strategy comes to this sort of perfection, it is not enough simply to demonstrate that it can search an apparently difficult landscape quickly. After all, it might be that the assumptions made by the search strategy just happen to match the characteristics of the landscape. Such a demonstration does not allow one to infer anything general about the strategy’s ability to learn while searching.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1987 Kluwer Academic Publishers
About this chapter
Cite this chapter
Ackley, D.H. (1987). Empirical demonstrations. In: A Connectionist Machine for Genetic Hillclimbing. The Kluwer International Series in Engineering and Computer Science, vol 28. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1997-9_3
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1997-9_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-9192-3
Online ISBN: 978-1-4613-1997-9
eBook Packages: Springer Book Archive