Artículos relacionados a A Connectionist Machine for Genetic Hillclimbing: 28...

A Connectionist Machine for Genetic Hillclimbing: 28 (The Springer International Series in Engineering and Computer Science) - Tapa blanda

Ackley, David

 
9781461291923: A Connectionist Machine for Genetic Hillclimbing: 28 (The Springer International Series in Engineering and Computer Science)
Tapa blanda
ISBN 10: 1461291925 ISBN 13: 9781461291923
Editorial: Springer, 2011

Sinopsis

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.

"Sinopsis" puede pertenecer a otra edición de este libro.

Críticas

` 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

Reseña del editor

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.

"Sobre este título" puede pertenecer a otra edición de este libro.

Editorial
Springer
Año de publicación
2011
Idioma
Inglés
ISBN 10 
1461291925
ISBN 13 
9781461291923
Encuadernación
Tapa blanda
Número de páginas
280
Contacto del fabricante
Springer Nature Customer Service Center GmbH
ProductSafety@springernature.com

Europaplatz 3
Heidelberg
69115
Alemania