Abstract
In this paper, a simple parallel cross-validation method for estimating the optimal number of hidden units for multi-layered feedforward neural network models trained by the generalized delta learning rule is presented. A neural network model is considered optimal when an ideal compromise between modelling accuracy (bias) and generalizing ability (variance) is found. The problem of training by means of gradient descent based methods, on data containing local minima is adressed. The cross-validation program has been parallelized to operate in a local area computer network. Development and execution of the parallel application was aided by the HYDRA
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
Allen, D.M. The relationship between variable selection and data augmentation and a method for predictions. Technometrics, 16: 125–127, 1974.
Geisser, S. The predictive sample reuse method with applications. Journal of the American Statistical Association, 70: 320–328, 1975.
Stone, M. Cross-validatory choice and assesment of statistical predictions. Journal of the Royal Statistical Society, 36: 111–133, 1974.
Wold, S. Cross-validatory estimation of the number of components in factor and principal components models. Technometrics, 20(4):397–405, november 1978.
Melssen, W.J., Derks, E.P.P.A., Beckers, M.L.M., and Buydens, L.M.C. Parallel processing in a local area network of computers. part i. hydra: concept, configuration and implementation of parallel applications. Computers & Chemistry, 1995. submitted.
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
Derks, E.P.P.A., Melssen, W., Buydens, L.M.C. (1995). Parallel Cross-Validation of Artificial Neural Networks. 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_70
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3087-1_70
Publisher Name: Springer, London
Print ISBN: 978-3-540-19992-2
Online ISBN: 978-1-4471-3087-1
eBook Packages: Springer Book Archive