Abstract
Biological neural networks have developed over time through genetic evolution. It therefore seems plausible that evolutionary concepts could also be effective when applied to artificial neural networks. The central concepts of natural evolution are selection and mutation; however, when modeling biological systems these concepts must be augmented by the mechanisms of genetic reproduction, such as genetic recombination or crossover. Of course, the use of genetic operators need not be restricted to biological modeling. In fact, the application of these concepts to machine learning, which was pioneered by John Holland in the 1970s [Ho75], has found widespread interest recently [Ho88a, Go88, Mo89, An94, Ma94a, Mc95a, Mi94, Qi94, Pr94].
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Müller, B., Reinhardt, J., Strickland, M.T. (1995). Evolutionary Algorithms for Learning. In: Neural Networks. Physics of Neural Networks. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57760-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-57760-4_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60207-1
Online ISBN: 978-3-642-57760-4
eBook Packages: Springer Book Archive