Abstract
As discussed in Sect. 6.4, feed-forward networks with hidden layers can represent any smooth continuous function ℝn → ℝm. As an illustration the program perfunc is designed to solve the following task: when presented with the values of a specimen g(x) out of a dass of one-dimensional functions at a set of points x i it predicts the function values at the output points x′ i . This is achieved by training the network with the error back-propagation algorithm by presenting various ‘patterns’ σ μ i where μ refers to specific values of the continuous parameters on which the function g(x) depends. The training method is essentially the same as was used for Boolean-function learning, so that its description need not be repeated. As a slight variation, the couplings w ij to the output layer are fed into linear transfer functions \( \tilde f\left( x \right)\,\, = \,\,x \). In contrast to the bounded sigmoidal function f(x) = tanh(βx) used for the interior layers, this enables the output signals S i to take on arbitrarily large values.
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
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Müller, B., Reinhardt, J. (1990). PERFUNC: Learning Continuous Functions with Back-Propagation. In: Neural Networks. Physics of Neural Networks. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-97239-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-97239-3_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-97241-6
Online ISBN: 978-3-642-97239-3
eBook Packages: Springer Book Archive