Computational Geosciences

, Volume 14, Issue 1, pp 199–206 | Cite as

Epoch determination for neural network by self-organized map (SOM)

  • Shivam Sinha
  • T. N. Singh
  • V. K. Singh
  • A. K. Verma
Original paper


Artificial neural networks have a wide application in many areas of science and engineering and, particularly, in geotechnical problems with some degree of success due to the fact that the mechanical behavior of rocks are not salient. They are highly nonlinear, quite complex and complicated. While applying neural network in such complicated problems, epoch determination is based on hit-and-trail basis mainly. In this paper, the effect of different number of epochs is shown on the network and a method is proposed to determine the optimum number of epoch with the help of self-organized map (SOM) to avoid overtraining of the network. Data distribution is also done with the help of SOM and a statistical analysis is made to show consistency between training and testing dataset for ensuring the optimal model performance.


Self-organizing map Artificial neural network Supervised learning Unsupervised learning Kohonen network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ghaboussi, J., Garrett, J.H. Jr., WU, X.: Knowledge-based modeling of material behavior with neural networks. J. Eng. Mech. ASCE 117(1), 132–53 (1991)CrossRefGoogle Scholar
  2. 2.
    Ellis, G.W., Yao, C., Zhao, R.: Neural network modeling of the mechanical behavior of sand. In: Proc., 9th Conf., ASCE Eng. Mech., pp. 421–424. ASCE, N. Y. (1992)Google Scholar
  3. 3.
    Toll, D.: Artificial Intelligence Applications in Geotechnical Engineering. Geotechnical System Group, University of Durham, Durham (1996)Google Scholar
  4. 4.
    Arora, V.K.: Strength and deformation behavior of jointed rocks. Ph.D. thesis, Indian Institute of Technology, Delhi, India (1987)Google Scholar
  5. 5.
    Yaji, R.K.: Shear strength and deformation of jointed rocks. Ph.D. thesis, Indian Institute of Technology, New Delhi, India (1984)Google Scholar
  6. 6.
    Roy, N.: Engineering behavior of rock masses through study of jointed models. Ph.D. thesis, Indian Institute of Technology, Delhi, India (1993)Google Scholar
  7. 7.
    Einstein, H.H., Hirscfeld, R.C.: Models studies in mechanics of jointed rocks. J. Soil Mech. Found. Div. ASCE 99, 229–248 (1973)Google Scholar
  8. 8.
    Brown, E.T., Trollope, D.H.: Strength of models of jointed rock. J. Soil Mech. Found. Div. ASCE SM2 96, 685–704 (1970)Google Scholar
  9. 9.
    Demuth, H., Beale, M.: Neural Network Toolbox for Use with MATLAB. MathWorks, Natick (1998)Google Scholar
  10. 10.
    Beale, R., Jackson, T.: Neural Computing: An Introduction, p. 240. Adam Hilger, Bristol (1990)MATHCrossRefGoogle Scholar
  11. 11.
    Kohonen, T.: Self-organization and Associative Memory. Springer, Berlin (1984)MATHGoogle Scholar
  12. 12.
    Sirat, M., Tablot, C.J.: Application of artificial neural networks to fracture analysis at the Aspo HRL, Sweden: fracture sets classification. Int. J. Rock Mech. Min. Sci. 38, 621–639 (2001)CrossRefGoogle Scholar
  13. 13.
    Kocjancic, R., Zupan, J.: Modeling of river flow rate: the influence of the training set selection. Chemom. Intell. Lab. Syst. 54, 21–34 (2000)CrossRefGoogle Scholar
  14. 14.
    Bowden, G.J., Maier, H.R., Dandy, G.C.: Optimal division of data for neural network models in water resources applications. Water Resour. Res. 38(2), 2.1–2.11 (2002)CrossRefGoogle Scholar
  15. 15.
    Shahin, M.A., Maier, H.R., Jaska, M.B.: Data division for developing neural networks applied to geotechnical engineering. J. Comput. Civ. Eng. ASCE 18(2), 105–114 (2004)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  • Shivam Sinha
    • 1
  • T. N. Singh
    • 2
  • V. K. Singh
    • 1
  • A. K. Verma
    • 2
  1. 1.Institute of TechnologyBanaras Hindu UniversityVaranasiIndia
  2. 2.Department of Earth SciencesIndian Institute of Technology BombayMumbaiIndia

Personalised recommendations