Abstract
Training local models is a comparably simple task. Optimizing the kernel shape such that local models fit well to the underlying data, on the other hand, can be a demanding challenge. In XCSF, the Genetic Algorithm (GA) is responsible for this optimization and the subtle mechanisms in the fitness estimation guide the GA towards a balance between accuracy and generalization. This chapter is concerned with challenging problems, where XCSF may not find an accurate solution out of the box.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2014 Springer Fachmedien Wiesbaden
About this chapter
Cite this chapter
Stalph, P. (2014). Evolutionary Challenges for XCSF. In: Analysis and Design of Machine Learning Techniques. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-04937-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-658-04937-9_6
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-04936-2
Online ISBN: 978-3-658-04937-9
eBook Packages: EngineeringEngineering (R0)