Abstract
Recent developments in neural network theory show that multi-layer feed-forward neural networks with one hidden layer of neurons can be used to approximate any multi-dimensional function to any desired accuracy, if a suitable number of neurons are included in the hidden layer and the correct interconnection weight values can be found [28].
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
© 1991 Springer Science+Business Media New York
About this chapter
Cite this chapter
Lee, TC. (1991). Multi-Layer Feed-Forward Networks. In: Structure Level Adaptation for Artificial Neural Networks. The Springer International Series in Engineering and Computer Science, vol 133. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3954-4_3
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3954-4_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6765-9
Online ISBN: 978-1-4615-3954-4
eBook Packages: Springer Book Archive