Abstract
This program illustrates the function of a feed-forward layered neural network as described in Chapts. 5–7. Its task is to learn an arbitrary Boolean function of a small number of Boolean variables. This is achieved by a three-layer feed-forward network which is trained by a gradient-descent method, i.e. by the rule of error back-propagation. The network consists of an input layer σ k , 1 ≤ k ≤ n in, a hidden layer s j , 1 ≤ j ≤ n hid, and an output layer S i , 1 ≤ i ≤ n out. The synaptic connections are \( {\bar w_{jk}} \) from the input to the hidden layer, and w ij from the hidden to the output layer. In addition there are activation thresholds \( {\bar \vartheta _j} \) and ϑ i . The neurons have two activation values chosen as −1 and +1 (the transformation to the values 0 and 1 commonly used to represent binary numbers is trivial).
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
© 1990 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Müller, B., Reinhardt, J. (1990). PERBOOL: Learning Boolean Functions with Back-Propagation. In: Neural Networks. Physics of Neural Networks. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-97239-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-97239-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-97241-6
Online ISBN: 978-3-642-97239-3
eBook Packages: Springer Book Archive