Using Taguchi's method of experimental design to control errors in layered perceptrons
- 1 July 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (4) , 949-961
- https://doi.org/10.1109/72.392257
Abstract
A significant problem in the design and construction of an artificial neural network for function approximation is limiting the magnitude and the variance of errors when the network is used in the field. Network errors can occur when the training data does not faithfully represent the required function due to noise or low sampling rates, when the network's flexibility does not match the variability of the data, or when the input data to the resultant network is noisy. This paper reports on several experiments whose purpose was to rank the relative significance of these error sources and thereby find neural network design principles for limiting the magnitude and variance of network errors.Keywords
This publication has 10 references indexed in Scilit:
- Generalization by weight-elimination applied to currency exchange rate predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Neural Networks and the Bias/Variance DilemmaNeural Computation, 1992
- Using additive noise in back-propagation trainingIEEE Transactions on Neural Networks, 1992
- Connectionist ideas and algorithmsCommunications of the ACM, 1990
- Novel backpropagation algorithm for reduction of hidden units and acceleration of convergence using artificial selectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Spline Models for Observational DataPublished by Society for Industrial & Applied Mathematics (SIAM) ,1990
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Statistical predictor identificationAnnals of the Institute of Statistical Mathematics, 1970