Abstract
This paper proposes an application independent method of automating learning rule parameter selection using a group of supervisor neural networks, known as meta neural networks, to alter the value of a learning rule parameter during training. Each meta neural network is trained using data generated by observing the training of a neural network and recording the effects of the selection of various parameter values. A group of meta neural networks is then polled to obtain a parameter value for a learning rule. Experiments are undertaken to see how this method performs by using it to adapt a global parameter of RPROP.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
C. McCormack. A study of the adaptation of learning rule parameters using a meta neural network. In 13th European Meeting on Systems and Cybernetic Research, volume 2, pages 1043–1048, 1996.
C. McCormack. Using a meta neural network for RPROP parameter adaptation. In Proc. European Symposium on Artificial Neural Networks, pages 7–12, 1996.
I. Pitas. Parallel Algorithms for Digital Image Processing, Vision and Neural Networks. John Wiley and Sons, Chichester, 1993.
L. Prechelt. PROBEN1: A set of neural network benchmarking rules. Technical Report 21/94, Dept. of Informatics, University of Karlsruhe, Germany, 1994. ftp://ftp.ira.uka.de/pub/neuron/probenl.tar.gz.
M. Riedmiller. Advanced supervised learning in multilayered perceptrons: Prom backpropagation to adaptive learning algorithms. Computer Standards and Interfaces, 16:265–278, 1994.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Wien
About this paper
Cite this paper
McCormack, C. (1998). A Meta Neural Network Polling System for the RPROP Learning Rule. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6492-1_111
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6492-1_111
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83087-1
Online ISBN: 978-3-7091-6492-1
eBook Packages: Springer Book Archive