Skip to main content
SpringerLink
Log in
Book cover

A Connectionist Machine for Genetic Hillclimbing

  • Book
  • © 1987
Download book PDF

Overview

Authors:
  1. David H. Ackley

    1. Carnegie Mellon University, USA

    View author publications

    You can also search for this author in PubMed   Google Scholar

Buy print copy

Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Table of contents (8 chapters)

  1. Front Matter

    Pages i-xiii
    Download chapter PDF

  2. Introduction

    • David H. Ackley
    Pages 1-28
    Download chapter PDF

  3. The model

    • David H. Ackley
    Pages 29-70
    Download chapter PDF

  4. Empirical demonstrations

    • David H. Ackley
    Pages 71-102
    Download chapter PDF

  5. Analytic properties

    • David H. Ackley
    Pages 103-131
    Download chapter PDF

  6. Graph partitioning

    • David H. Ackley
    Pages 133-153
    Download chapter PDF

  7. Related work

    • David H. Ackley
    Pages 155-189
    Download chapter PDF

  8. Limitations and variations

    • David H. Ackley
    Pages 191-201
    Download chapter PDF

  9. Discussion and conclusions

    • David H. Ackley
    Pages 203-230
    Download chapter PDF

  10. Back Matter

    Pages 231-260
    Download chapter PDF
Back to top

Keywords

About this book

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.

Reviews

` 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

Authors and Affiliations

  • Carnegie Mellon University, USA

    David H. Ackley

Bibliographic Information

  • Book Title: A Connectionist Machine for Genetic Hillclimbing

  • Authors: David H. Ackley

  • Series Title: The Springer International Series in Engineering and Computer Science

  • DOI: https://doi.org/10.1007/978-1-4613-1997-9

  • Publisher: Springer New York, NY

  • eBook Packages: Springer Book Archive

  • Copyright Information: Kluwer Academic Publishers 1987

  • Hardcover ISBN: 978-0-89838-236-5Published: 31 August 1987

  • Softcover ISBN: 978-1-4612-9192-3Published: 17 October 2011

  • eBook ISBN: 978-1-4613-1997-9Published: 06 December 2012

  • Series ISSN: 0893-3405

  • Edition Number: 1

  • Number of Pages: XIV, 260

  • Topics: Artificial Intelligence

Publish with us

Policies and ethics

Back to top

Search

Navigation