1. Home

The Influence of Hidden Neurons Factor on Neural Nework Training Quality Assurance

Peter Grabusts, Aleksejs Zorins

Abstract


The work shows the role of hidden neurons in the multilayer feed-forward neural networks. The numeric expression of hidden neurons is usually determined in each case empirically. The methodology for determining the number of hidden neurons are described. The neural network based approach is analyzed using a multilayer feed-forward network with backpropagation learning algorithm. We have presented neural network implementation possibility in bankruptcy prediction (the experiments have been performed in the Matlab environment). On the base of bankruptcy data analysis the effect of hidden neurons to specific neural network training quality is shown. The conformity of theoretical hidden neurons to practical solutions was carried out.

Keywords


bankruptcy prediction; financial ratio; hidden neurons; neural networks; backpropagation

Full Text:

PDF

References


T. Masters, Practical Neural Network recipes in C++. Academic Press, 1993.

I. Alexander and H. Morton, An Introduction to Neural Computing. Chapman & Hall, London, 1991.

J. Hertz, A. Krogh and R.G. Palmer, Introduction to the theory of neural computation. Addison Wesley, 1991.

M. Odom and R. Sharda R, A neural network model for bankruptcy prediction, In Proc, Int. Joint Conf, Neural Networks, San Diego, CA, 1990.

E. Altman E, "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy," Journal of Finance, vol. 13, pp.589-609, 1968.

E. Altman, R. Haldeman and P. Narayanan, "ZETA analysis. A new model to identify bankruptcy risk of corporations," Journal of Banking and Finance 1, pp. 29-54, 1977.

A. Atiya A, "Bankruptcy prediction for credit risk using neural networks: A survey and new results, " IEEE Transactions on Neural Networks, Vol. 12, No. 4, pp. 929-935, 2001.

B. Back, T. Laitinen and K. Sere, "Neural networks and bankruptcy prediction: funds flow, accrual ratios and accounting data, " Advances in Accounting 14, pp. 23-37, 1996.

E.B. Baum and D. Haussler, "What size net gives valid generalization," Neural Computation, 1, pp. 151-160, 1988.

R. Beaver, "Financial ratios as predictors of failure. Empirical Research in Accounting: Selected Studies," Accounting Research, vol. 4, pp.71-111, 1966.

K. Gnana Sheela and S.N. Deepa, "Review on Methods to Fix Number of Hidden Neurons in Neural Networks," Mathematical Problems in Engineering, Volume 2013.

P.Grabusts, "Analysing Bankruptcy Data with Neural Networks," 10th International Conference on Soft Computing, Mendel2004, Brno, Czech Republic, June 16.-18., pp.111-117, 2004.

J.M. Kinser J.M., „The determination of Hidden Neurons,” Optical Memories and Neural Networks, 5(4), 245-262, 1996.

J. Ohlson J, "Financial ratios and the probabilistic prediction of bankruptcy," Accounting Res, vol. 18, pp. 109-131, 1980.

G. Rudorfer G, "Early bankruptcy detecting using neural networks," APL Quote Quad, ACM New York, vol. 25, N. 4, pp. 171-178, 1995.

D.E. Rumelhart, G.E. Hinton and R.J. Williams, "Learning representations by backpropagating errors," Nature, 323(9):533-536, 1986.

K. Tam and M. Kiang, "Managerial applications of the neural networks: The case of bank failure predictions," Management Science, vol. 38, pp. 416-430, 1992.

"Bankruptcy data," [Online]. Available: http://godefroy.sdf-eu.org/apl95/ratios95.zip [Accessed: March 30, 2015].




DOI: https://doi.org/10.17770/etr2015vol3.213

Refbacks

  • There are currently no refbacks.


SCImago Journal & Country Rank
Rēzeknes Tehnoloģiju akadēmija, 2016 © Atbrīvošanas aleja 115, Rēzekne, Latvija. Tālrunis: 28325368;
Jautājumus un ierosinājumus sūtiet uz helpdesk@rta.lv