Abstract
Taking use of BP neural network theory, a cyclic search method between dynamic training samples number and dynamic hidden nodes number is proposed to improve the prediction accuracy of network model. By increasing the training samples one by one to control the network training, searching dynamic sample error expectation matrix, and finally getting the best training sample number, with the goal of minimum error expectations. Thus, through the optimization model of hidden nodes number, searching the number of hidden layer nodes of network minimum output error. The results of the analysis of examples shows that, with the increasing number of training samples, the network output error expectation experienced three stages, namely recurrent big error stage, yield decline error stage and stable small error stage. But with the increasing number of hidden layer nodes, the result is on the contrary. This shows that proper number of training samples and hidden layer nodes is of great significance to improving the output precision of neural network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
du Jardin P (2010) The influence of variable selection techniques on model accuracy. J Neurocomput 73:2047–2060
Jung J-Y, Phil HL (2006) A neural network model for maximizing prediction accuracy in haplotype tagging SNP selection C 2006 In: International joint conference on neural networks, pp 2303–2307
Guo C (2005) Analysis of influence factors for forecasting precision of artificial neural network model and its optimizing. J Patt Recogn Artif Intell 18(5):2303–2307
Song S, Bai J The Local Impact Analysis in Artificial Neural Networks. J Value Eng 1(7):144–145
Wu W, Chen W (2005) Predict stock price based on BP neural network. J Dalian Univ Technol 41(1):9–15
Cai F, Yu J (2011) BP neural network based on grey prediction of gas explosion. J Autom 27(5):42–43
Mirchandani G, Cao W (1989) On hidden nodes for neural nets. IEEE Trans Circuits Syst 36(5):661–664
Wanas N, Auda G (1998) On the optimal number of hidden nodes in a neural network. In: Canadian conference on electrical and computer engineering, vol. 2, pp 918–921
Gao Y (2008) Study of tooth root stress calculation method based on neural network. May 2008, pp 39–48
Feng Y, Wu B (2012) Study on forecasting typhoon rainfall based on BP neural network. Res Soil Water Conserv 19(3):289–293
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, C., Xu, C. (2013). Optimization Analysis of Dynamic Sample Number and Hidden Layer Node Number Based on BP Neural Network. In: Yin, Z., Pan, L., Fang, X. (eds) Proceedings of The Eighth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), 2013. Advances in Intelligent Systems and Computing, vol 212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37502-6_82
Download citation
DOI: https://doi.org/10.1007/978-3-642-37502-6_82
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37501-9
Online ISBN: 978-3-642-37502-6
eBook Packages: EngineeringEngineering (R0)