Design optimal neural network based on new LM training algorithm for solving 3D - PDEs
DOI:
https://doi.org/10.11121/ijocta.1519Keywords:
Partial Differenstial Equations, Neural networks, BP-training algorithm, Unconstrained optimization, LM training algorithm, Convergence analysisAbstract
In this article, we design an optimal neural network based on new LM training algorithm. The traditional algorithm of LM required high memory, storage and computational overhead because of it required the updated of Hessian approximations in each iteration. The suggested design implemented to converts the original problem into a minimization problem using feed forward type to solve non-linear 3D - PDEs. Also, optimal design is obtained by computing the parameters of learning with highly precise. Examples are provided to portray the efficiency and applicability of this technique. Comparisons with other designs are also conducted to demonstrate the accuracy of the proposed design.
Downloads
References
Salih, H., Tawfiq, L. N. M., Yahya, Z. R., & Zin, S. M. (2018). Solving modified regularized long wave equation using collocation method. Journal of Physics: Conference Series, 1003(1), 012062. https://doi.org/10.1088/1742-6596/1003/1/012062
Hussein, N.A., & Tawfiq L. N.M. (2023). Exact soliton solution for systems of non-linear (2+1)D- DEs. AIP Conference Proceedings, 2834(1), 1-7.
Jabber, A. K., & Tawfiq, L. N. M. (2018). New transform fundamental properties and its applications. Ibn Alhaitham Journal for Pure and Applied Science, 31(1), 151-163. https://doi.org/10.30526/31.2.1954
Ali, S., Khan, A., Shah, K., Alqudah, M. A., & Abdeljawad, T. (2022). On computational analysis of highly nonlinear model addressing real world applications. Results in Physics, 36, 105431. https://doi.org/10.1016/j.rinp.2022.105431
Gul, H., Alrabaiah, H., Ali, S., Shah, K., & Muhammad, S. (2020). Computation of solution to fractional order partial reaction diffusion equations. Journal of Advanced Research, 25, 31-38. https://doi.org/10.1016/j.jare.2020.04.021
Tawfiq, L. N., & Hussein, N. A. (2023). Efficient approach for solving (2+ 1) D-differential equations. Baghdad Science Journal, 20(1), 0166-0166. https://doi.org/10.21123/bsj.2022.6541
Enadi, M. O., & Tawfiq, L. N. M. (2019). New approach for solving three dimensional space partial differential equation. Baghdad Science Jour- nal, 16(3), 786-792. https://doi.org/10.21123/bsj.2019.16.3(Suppl.).0786
Tawfiq, L. N. M., & Altaie, H. (2020). Recent modification of homotopy perturbation method for solving system of third order PDEs. Journal of Physics: Conference Series, 1530(1), 1-7. https://doi.org/10.1088/1742-6596/1530/1/012073
Ghazi, F. F. (2020). Modeling the contamination of soil adjacent to Mohammed AL-Qassim highway in Baghdad. Iraqi Journal of Science, 61(10), 2663-2670. https://doi.org/10.24996/ijs.2020.61.10.23
Tawfiq, L. N. M., & Kareem, Z. H. (2021). Efficient modification of the decomposition method for solving a system of PDEs. Iraqi Journal of Science, 62(9), 3061-3070. https://doi.org/10.24996/ijs.2021.62.9.21
Kareem, Z. H., & Tawfiq, L. N. M. (2020). Recent modification of decomposition method for solving nonlinear partial differential equations. Journal of Advances in mathematics, 18, 154-161. https://doi.org/10.24297/jam.v18i.8744
Kareem, Z. H., & Tawfiq, L. N. M. (2023). Recent modification of decomposition method for solving wave-like Equation. Journal of Interdisciplinary Mathematics, 26(5), 809-820. https://doi.org/10.47974/JIM-1235
Tawfiq, L. N., & Hussein, N. A. (2022). Exact solution for systems of nonlinear (2+ 1) D- differential equations. Iraqi Journal of Science, 63(10), 4388-4396. https://doi.org/10.24996/ijs.2022.63.10.25
Tawfiq, L. N. M., & Abed, A. I. (2021). Efficient method for solving fourth order PDEs. Jour- nal of Physics: Conference Series, 1818(1), 1-10. https://doi.org/10.1088/1742-6596/1818/1/012166
Kareem, Z.H., & Tawfiq, L. N.M. (2022). New modification of decomposition method for solving high order strongly nonlinear partial differential equations. AIP Conference Proceedings, 2398(1), 1-9.
Hussein, N. A., & Tawfiq, L. N. M. (2020, May). New approach for solving (1+ 1)-dimensional differential equation. Journal of Physics: Confer- ence Series, 1530(1), 1-11. https://doi.org/10.1088/1742-6596/1530/1/012098
Tawfiq, L. N., & Yassien, S. M. (2013). Solution of high order ordinary boundary value problems using semi-analytic technique. Ibn Al-Haitham Journal for Pure & Applied Sciences, 26(1), 281- 291.
Hussein, N.A., & Tawfiq, L.N.M. (2022). Efficient approach for solving high order (2+1) D- differential equation. AIP Conference Proceedings, 2398(1), 1-11. https://doi.org/10.1063/5.0093671
Salih, H., & Tawfiq, L. (2020, November). Solution of modified equal width equation using quartic trigonometric-spline method. Journal of Physics: Conference Series, 1664(1), 1-10. https://doi.org/10.1088/1742-6596/1664/1/012033
Tawfiq, L. N. M., & Khamas, A. H. (2020, May). New coupled method for solving Burger’s equation. Journal of Physics: Conference Series, 1530(1), 1-11. https://doi.org/10.1088/1742-6596/1530/1/012069
Tawfiq, L. N. M., & Khamas, A. H. (2023). New approach for calculate exponential integral function. Iraqi Journal of Science, 64(8), 4034-4042. https://doi.org/10.24996/ijs.2023.64.8.27
Tawfiq, L. N. M., Al-Noor, N. H., & Al-Noor, T. H. (2019, September). Estimate the rate of contamination in baghdad soils by using numerical method. Journal of Physics: Conference Series, 1294(3), 1-11. https://doi.org/10.1088/1742-6596/1294/3/032020
Tawfiq, L. N., & Oraibi, Y. A. (2017). Fast training algorithms for feed forward neural networks. Ibn Al-Haitham Journal for Pure and Applied Sci- ence, 26(1), 275-280.
Tawfiq, L. N., & Hussein, A. A. (2013). Design feed forward neural network to solve singular boundary value problems. International Scholarly Research Notices, 2013, 1-7. https://doi.org/10.1155/2013/650467
Tawfiq, L. N. M., & Hussein, W. R. (2016). Design suitable neural network for processing face recognition. Global Journal of Engineering Science and Researches, 3(3), 58-64.
Tawfiq, L. N. M. (2017). The finite element neural network and its applications to forward and inverse problems. Ibn AL-Haitham Journal For Pure and Applied Science, 19(4), 109-124.
Tawfiq, L. N. M., & Salih, O. M. (2019). Design suitable feed forward neural network to solve Troesch’s problem. Sci. Int.(Lahore), 31(1), 41- 48.
Hussien, Z. (2020). Anomaly detection approach based on deep neural network and dropout. Baghdad Science Journal, 17(2 (SI)), 0701-0701. https://doi.org/10.21123/bsj.2020.17.2(SI).0701
Ali, M. H., & Tawfiq, L. N. (2023). Design optimal neural network for solving unsteady state confined aquifer problem. Mathematical Modelling of Engineering Problems, 10(2), 565-571. https://doi.org/10.18280/mmep.100225
Alia, M. H., & Tawfiqa, L. N. (2023). Novel neural network based on New modification of BFGS update algorithm for solving partial differential equations. Advances in the Theory of Nonlinear Analysis and its Applications, 7(4), 76-88.
Gupta, R., & Batra, C. M. (2022). Performance assessment of solar-transformer-consumption system using neural network approach. Baghdad Science Journal, 19(4), 0865-0865. https://doi.org/10.21123/bsj.2022.19.4.0865
Tawfiq, L. N. M., & Khamas, A. H. (2021). Determine the effect hookah smoking on health with different types of tobacco by using parallel processing technique. Journal of Physics: Conference Series, 1818(1), 1-10. https://doi.org/10.1088/1742-6596/1818/1/01217
Tawfiq, L. N. M., & Tawfiq, M. N. M. (2017). The effect of number of training samples for artificial neural network. Ibn AL-Haitham Journal For Pure and Applied Science, 23(3), 1-7.
Ghazi, F. F., & Tawfiq, L. N. M. (2020). New approach for solving two dimensional spaces PDE. Journal of Physics: Conference Series, 1530(1), 012066. https://doi.org/10.1088/1742-6596/1530/1/012066
Jamil, H.J., Albahri, M.R.A., Al-Noor, N.H., Al- Noor, T.H., Heydari, A.R., Rajan, A.K., Arnetz, J., Arnetz, B. & Tawfiq, L.N.M. (2020). Hookah smoking with health risk perception of different types of tobacco. Journal of Physics: Conference Series, 1664(1), 012127. https://doi.org/10.1088/1742-6596/1664/1/012127
Kareema, Z. H., & Tawfiqa, L. N. (2023). Solv- ing (3+ 1) D-New Hirota bilinear equation using tanh method and new modification of extended tanh method. Advances in the Theory of Nonlinear Analysis and its Applications, 7(4), 114-122.
Hussein, N. A., Helal, M. M., & Tawfiq, L. N. M. (2023). Double LA-transform and their properties for solving partial differential equations. AIP Conference Proceedings, 2834(1), 1-10
Kumar, A., Kumar, M., & Goswami, P. (2024). Numerical solution of coupled system of Emden- Fowler equations using artificial neural network technique. An International Journal of Optimization and Control: Theories & Applications, 14(1), 62-73. https://doi.org/10.11121/ijocta.1424
Okkan, U. (2011). Application of Levenberg- Marquardt optimization algorithm based multilayer neural networks for hydrological time series modeling. An International Journal of Optimization and Control: Theories & Applications, 1(1), 53-63. https://doi.org/10.11121/ijocta.01.2011.0038
Kumar, K., Parida, M., & Katiyar, V. K. (2011). Road traffic noise prediction with neural networks - A review. An International Journal of Optimization and Control: Theories & Applications, 2(1), 29-37. https://doi.org/10.11121/ijocta.01.2012.0059
Demirtas, M., & Alci, M. (2011). A comparative study of neural networks and fuzzy systems in modeling of a nonlinear dynamic system. An International Journal of Optimization and Control: Theories & Applications, 1(1), 65-73. https://doi.org/10.11121/ijocta.01.2011.0055
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Farah F. Ghazi, Luma N. M. Tawfiq
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in IJOCTA are made freely available online immediately upon publication, without subscription barriers to access. All articles published in this journal are licensed under the Creative Commons Attribution 4.0 International License (click here to read the full-text legal code). This broad license was developed to facilitate open access to, and free use of, original works of all types. Applying this standard license to your work will ensure your right to make your work freely and openly available.
Under the Creative Commons Attribution 4.0 International License, authors retain ownership of the copyright for their article, but authors allow anyone to download, reuse, reprint, modify, distribute, and/or copy articles in IJOCTA, so long as the original authors and source are credited.
The readers are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
- for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
This work is licensed under a Creative Commons Attribution 4.0 International License.
