Abstract
In the dissertation so far, function optimization has been introduced as the task, and speed has been taken as the performance measure. SIGH has been motivated as a search strategy, and then formally defined as a connectionist learning machine. The primary empirical claim of the dissertation has been demonstrated: Across a non-trivial range of functions, SIGH is an effective competitor measured against a field of non-trivial search strategies. Some relationships to existing work have been discussed, and some limitations and possible variations have been presented.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
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). Discussion and conclusions. 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_8
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1997-9_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-9192-3
Online ISBN: 978-1-4613-1997-9
eBook Packages: Springer Book Archive