Abstract
Multilayered networks (MLNs) can be used for pattern classification and function approximation. In this chapter first we discuss how to train the network. Then we clarify the advantages and disadvantages of the network and discuss methods for overcoming these disadvantages while evaluating its performance for some applications: determination of the optimal structure; synthesis of the network for pattern classification; extraction of a pattern classification algorithm from the trained network; and acceleration of network training.
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
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Abe, S. (1997). Multilayered Networks. In: Neural Networks and Fuzzy Systems. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6253-5_3
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6253-5_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7869-3
Online ISBN: 978-1-4615-6253-5
eBook Packages: Springer Book Archive