Design Feed Forward Neural network for solving two dimension singularly perturbed integro-differential and integral equation

  • Authors

    • Eman Ali Hussain Department of Mathematics, College of Science, University of AL-Mustansiriyah , Iraq
    • Nahdh S.M. Al_saif Al_anbar university,iraq
    2013-02-22
    https://doi.org/10.14419/ijamr.v2i1.665
  • Recently, there has been an increasing interest in the study of singular and perturbed systems. In this paper design fast feed forward neural network to present a method to solve two dimensions singularly perturbed integro-differential and integral equations. Using a multi-layer having one hidden layer with 7 hidden units (neurons) and one linear output unit the sigmoid activation of each unit is radial basis function and Levenberg – Marquardt (trainlm) training algorithm. Finally the results of numerical experiments are compared with the exact solution in illustrative examples to confirm the accuracy and efficiency of the presented scheme.

    Author Biographies

    • Eman Ali Hussain, Department of Mathematics, College of Science, University of AL-Mustansiriyah , Iraq
      Department of mathematics,
    • Nahdh S.M. Al_saif, Al_anbar university,iraq

      department of mathematic

  • Downloads

  • How to Cite

    Hussain, E. A., & Al_saif, N. S. (2013). Design Feed Forward Neural network for solving two dimension singularly perturbed integro-differential and integral equation. International Journal of Applied Mathematical Research, 2(1), 134-139. https://doi.org/10.14419/ijamr.v2i1.665