Abstract
This paper presents a general, problem-independent learning strategy for neural networks, based on Rechenberg's evolutionary strategy ([Rechenberg 73]). The main innovation of the evolutionary strategy proposed is that the optimization always works with a subset of object variables. The size of this subspace is controlled adaptively. My experiments showed that a learning strategy based exclusively on evolutionary algorithms only works properly if some modifications are made to the original algorithms. These are described in the section “Adaptive Selection of the Object Variables”.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Hinton, G. E. (1987). Connectionist Learning Procedures. Technical Report CMU-CS-87-115. Carnegie-Mellon University. Pittsburgh PA 15213.
Minsky, M. & Papert, S. (1969). Perceptrons. Cambridge, MA. MIT Press.
Rechenberg, I. (1973). Evolutionsstrategie. Stuttgart-Bad Cannstadt. Problemata Frommann — Holzboog.
Rumelhart, D. E., Hinton G. E., Williams, R. J. (1986) Learning internal representations by error propagation. In Parallel Distributed Processing, Chapter 8. MIT Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Scholz, M. (1991). A learning strategy for neural networks based on a modified evolutionary strategy. In: Schwefel, HP., Männer, R. (eds) Parallel Problem Solving from Nature. PPSN 1990. Lecture Notes in Computer Science, vol 496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0029770
Download citation
DOI: https://doi.org/10.1007/BFb0029770
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54148-6
Online ISBN: 978-3-540-70652-6
eBook Packages: Springer Book Archive