A Connectionist Machine for Genetic Hillclimbing (The Springer International Series in Engineering and Computer Science, 28)

Ackley, David

ISBN 10: 089838236X / ISBN 13: 9780898382365

Published by Springer, 1987

About this Item

Satisfaction Guaranteed or your money back.

Seller Inventory # 089838236X

Bibliographic Details

• Title: A Connectionist Machine for Genetic Hillclimbing (The Springer International Series in Engineering and Computer Science, 28)
• Publisher: Springer
• Publication Date: 1987
• Language: English
• ISBN 10: 089838236X
• ISBN 13: 9780898382365
• Binding: Hardcover
• Condition: New

About this title

Synopsis

In the "black box function optimization" problem, a search strategy is required to find an extremal point of a function without knowing the structure of the function or the range of possible function values. Solving such problems efficiently requires two abilities. On the one hand, a strategy must be capable of learning while searching: It must gather global information about the space and concentrate the search in the most promising regions. On the other hand, a strategy must be capable of sustained exploration: If a search of the most promising region does not uncover a satisfactory point, the strategy must redirect its efforts into other regions of the space. This dissertation describes a connectionist learning machine that produces a search strategy called stochastic iterated genetic hillclimb­ ing (SIGH). Viewed over a short period of time, SIGH displays a coarse-to-fine searching strategy, like simulated annealing and genetic algorithms. However, in SIGH the convergence process is reversible. The connectionist implementation makes it possible to diverge the search after it has converged, and to recover coarse-grained informa­ tion about the space that was suppressed during convergence. The successful optimization of a complex function by SIGH usually in­ volves a series of such converge/diverge cycles.

Review

` It is a good source for those interested in a concrete application of Boltzmann machines or (at several places) thoughtful treatise on their potential impact on the broader fields of artificial intelligence and machine learning. '
B.P. Buckles, Computing Reviews, January 1989