Abstract
We propose an efficient procedure for constructing and training a feed-forward neural network with a single hidden layer. The procedure can also be extended to construct neural networks with binary-valued weights.
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.
References
M. Marchand, M. Golea and P. Rujan, Europhysics Letters 11(1990)487–492.
M. Frean, Neural Computation 2(1990)198–209.
W. Krauth and M. Mezard, J. Phys. A20(1987)L745–L752.
S. J. Nowlan and G.E. Hinton, Neural Computation 4(1992)473–493.
C. Campbell and C. Perez Vicente, Neural Computation 7 (to appear); C.Campbell and C. Perez Vicente, “Constructing Feed-Forward Neural Networks for Binary Classification Tasks” Proceedings ESANN’95, D. Facto Publications, Brussels, 1995, p. 241–246.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag London Limited
About this paper
Cite this paper
Campbell, C., Coombes, S., Surkan, A. (1995). A Constructive Algorithm for Building a Feed-Forward Neural Network. In: Kappen, B., Gielen, S. (eds) Neural Networks: Artificial Intelligence and Industrial Applications. Springer, London. https://doi.org/10.1007/978-1-4471-3087-1_38
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3087-1_38
Publisher Name: Springer, London
Print ISBN: 978-3-540-19992-2
Online ISBN: 978-1-4471-3087-1
eBook Packages: Springer Book Archive