International Journal of Fuzzy Logic and Intelligent Systems

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Neural Network Training Using a GMDH Type Algorithm

  • Pandya, Abhijit S. (Dept. of Computer Science & Engineering, Florida Atlantic University) ;
  • Gilbar, Thomas (Department of Electrical and Computer Engineering, University of West Florida) ;
  • Kim, Kwang-Baek (Department of Computer Engineering, Silla University)
  • Published : 2005.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

Keywords

References

  1. A. S. Pandya and R. B. Macy, Pattern Recognition using Neural Networks in C++, IEEE Press and CRC Press, 1995
  2. A.G.Ivakhnenko, 'Heuristic self-organization in problems of engineering cybernetics', Automatica, Vol. 6, No.2, pp.207-219, 1970 https://doi.org/10.1016/0005-1098(70)90092-0
  3. Acock M.C. and Pachepsky Y.A, 'Estimating Missing Weather Data for Agricultural Simulations Using Group Method of Data Handling', Journal of Applied Meteorology, Vol. 39, pp.1176-1184, 2000 https://doi.org/10.1175/1520-0450(2000)039<1176:EMWDFA>2.0.CO;2
  4. T.Kondo, A.S.Pandya, J.M.Zurada, 'Logistic GMDH-type neural networks and their application to the identification of the X-ray film characteristic curve', Proc. of IEEE International Conference on System, Man, and Cybernetics, pp.437-442, 1999 https://doi.org/10.1109/ICSMC.1999.814131
  5. T. Kondo, A.S. Pandya, 'GMDH-type Neural Network Algorithm with Sigmoid Functions', International Journal of Knowledge-Based Engineering Systems, Vol. 7, No.4, pp.198-205,2003
  6. Draper N.R. and Smith H., Applied Regression Analysis. John Wiley & Sons, Inc., New York, New York, 1966
  7. K. B. Kim, H. W. Yun, 'A Study on Recognition of Brochogenic Cancer Cell Image Using a New Physiological Fuzzy Neural Networks,' Japanese Journal of Medical Electronics and Biological Engineering, Vol.13, No.5,pp.39-43, 1999
  8. T. Kondo, 'Revised GMDH type neural networks with radial basis functions and their application to medical image recognition of stomach', System Analysis Modelling Simulation, Vol.43, No. 10, pp.1363-1376, 2003 https://doi.org/10.1080/02329290290290024376
  9. K. B. Kim, Y. j. Kim, 'Recognition of English Calling Cards by Using Enhanced Fuzzy Radial Basis Function Neural Networks,' IEICE Trans. Fundamentals of Electronics, Communications and Computer Sciences, Vol.E87-A, No.6, pp.1355-1362, 2004
  10. Wu P, Fang S, Nuttle H., 'Efficient Neural Network Learning Using Second Order Information with Fuzzy Control', Neurocomputing, 43, pp 197-217,2002 https://doi.org/10.1016/S0925-2312(01)00336-8
  11. Hogstrom, K., Study on Strength Parameters for Agrrerates from South Western Swedish Rocks, Research Report, Chalmers University of Technology, Gotzborg, Sweden, 1994
  12. Huang Y., 'Application of Artificial Neural Networks To Predictions of Aggregate Quality Parameters', International Journal of Rock Mechanics and Mining Sciences, 36, pp. 551-561, 1999 https://doi.org/10.1016/S0148-9062(99)00028-5
  13. H.Akaike, 'A new look at the statistical model identification' IEEE Trans. Automatic Control, Vol.AC19, No.6, pp.716-723, 1974

Cited by

  1. Fourier and wavelet transformations application to fault detection of induction motor with stator current vol.17, pp.1, 2010, https://doi.org/10.1007/s11771-010-0016-4