IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i11p1827-d824652.html
   My bibliography  Save this article

Neural Network Algorithm with Dropout Using Elite Selection

Author

Listed:
  • Yong Wang

    (School of Computer Science and Technology, Ocean University of China, Qingdao 266100, China)

  • Kunzhao Wang

    (School of Computer Science and Technology, Ocean University of China, Qingdao 266100, China)

  • Gaige Wang

    (School of Computer Science and Technology, Ocean University of China, Qingdao 266100, China)

Abstract

A neural network algorithm is a meta-heuristic algorithm inspired by an artificial neural network, which has a strong global search ability and can be used to solve global optimization problems. However, a neural network algorithm sometimes shows the disadvantage of slow convergence speed when solving some complex problems. In order to improve the convergence speed, this paper proposes the neural network algorithm with dropout using elite selection. In the neural network algorithm with dropout using elite selection, the neural network algorithm is viewed from the perspective of an evolutionary algorithm. In the crossover phase, the dropout strategy in the neural network is introduced: a certain proportion of the individuals who do not perform well are dropped and they do not participate in the crossover process to ensure the outstanding performance of the population. Additionally, in the selection stage, a certain proportion of the individuals of the previous generation with the best performance are retained and directly enter the next generation. In order to verify the effectiveness of the improved strategy, the neural network algorithm with dropout using elite selection is used on 18 well-known benchmark functions. The experimental results show that the introduced dropout strategy improves the optimization performance of the neural network algorithm. Moreover, the neural network algorithm with dropout using elite selection is compared with other meta-heuristic algorithms to illustrate it is a powerful algorithm in solving optimization problems.

Suggested Citation

  • Yong Wang & Kunzhao Wang & Gaige Wang, 2022. "Neural Network Algorithm with Dropout Using Elite Selection," Mathematics, MDPI, vol. 10(11), pages 1-17, May.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:11:p:1827-:d:824652
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/11/1827/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/11/1827/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sergeyev, Yaroslav D. & Kvasov, Dmitri E. & Mukhametzhanov, Marat S., 2017. "Operational zones for comparing metaheuristic and deterministic one-dimensional global optimization algorithms," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 141(C), pages 96-109.
    2. Kvasov, Dmitri E. & Mukhametzhanov, Marat S., 2018. "Metaheuristic vs. deterministic global optimization algorithms: The univariate case," Applied Mathematics and Computation, Elsevier, vol. 318(C), pages 245-259.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Juan Li & Dan-dan Xiao & Hong Lei & Ting Zhang & Tian Tian, 2020. "Using Cuckoo Search Algorithm with Q -Learning and Genetic Operation to Solve the Problem of Logistics Distribution Center Location," Mathematics, MDPI, vol. 8(2), pages 1-32, January.
    2. R. Cavoretto & A. Rossi & M. S. Mukhametzhanov & Ya. D. Sergeyev, 2021. "On the search of the shape parameter in radial basis functions using univariate global optimization methods," Journal of Global Optimization, Springer, vol. 79(2), pages 305-327, February.
    3. Ziadi, Raouf & Bencherif-Madani, Abdelatif & Ellaia, Rachid, 2020. "A deterministic method for continuous global optimization using a dense curve," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 178(C), pages 62-91.
    4. Sergey S. Ketkov & Oleg A. Prokopyev & Lisa M. Maillart, 2023. "Planning of life-depleting preventive maintenance activities with replacements," Annals of Operations Research, Springer, vol. 324(1), pages 1461-1483, May.
    5. Linas Stripinis & Remigijus Paulavičius, 2023. "Novel Algorithm for Linearly Constrained Derivative Free Global Optimization of Lipschitz Functions," Mathematics, MDPI, vol. 11(13), pages 1-19, June.
    6. Jean Bigeon & Sébastien Le Digabel & Ludovic Salomon, 2021. "DMulti-MADS: mesh adaptive direct multisearch for bound-constrained blackbox multiobjective optimization," Computational Optimization and Applications, Springer, vol. 79(2), pages 301-338, June.
    7. Konstantin Barkalov & Irek Gubaydullin & Evgeny Kozinov & Ilya Lebedev & Roza Faskhutdinova & Azamat Faskhutdinov & Leniza Enikeeva, 2022. "On Solving the Problem of Finding Kinetic Parameters of Catalytic Isomerization of the Pentane-Hexane Fraction Using a Parallel Global Search Algorithm," Mathematics, MDPI, vol. 10(19), pages 1-13, October.
    8. Yan Liang & Xianzhi Hu & Gang Hu & Wanting Dou, 2022. "An Enhanced Northern Goshawk Optimization Algorithm and Its Application in Practical Optimization Problems," Mathematics, MDPI, vol. 10(22), pages 1-33, November.
    9. Umesh Balande & Deepti Shrimankar, 2019. "SRIFA: Stochastic Ranking with Improved-Firefly-Algorithm for Constrained Optimization Engineering Design Problems," Mathematics, MDPI, vol. 7(3), pages 1-26, March.
    10. Blondin, M.J. & Sicard, P. & Pardalos, P.M., 2019. "Controller Tuning Approach with robustness, stability and dynamic criteria for the original AVR System," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 163(C), pages 168-182.
    11. Kvasov, Dmitri E. & Mukhametzhanov, Marat S., 2018. "Metaheuristic vs. deterministic global optimization algorithms: The univariate case," Applied Mathematics and Computation, Elsevier, vol. 318(C), pages 245-259.
    12. Hassan M. Hussein Farh, 2024. "Neural Network Algorithm with Reinforcement Learning for Microgrid Techno-Economic Optimization," Mathematics, MDPI, vol. 12(2), pages 1-24, January.
    13. Wenyu Wang & Taimoor Akhtar & Christine A. Shoemaker, 2022. "Integrating $$\varepsilon $$ ε -dominance and RBF surrogate optimization for solving computationally expensive many-objective optimization problems," Journal of Global Optimization, Springer, vol. 82(4), pages 965-992, April.
    14. Babayan, Narek & Tahani, Mojtaba, 2019. "Team Arrangement Heuristic Algorithm (TAHA): Theory and application," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 166(C), pages 155-176.
    15. Jannatul Ferdous & Farid Bensebaa & Abbas S. Milani & Kasun Hewage & Pankaj Bhowmik & Nathan Pelletier, 2024. "Development of a Generic Decision Tree for the Integration of Multi-Criteria Decision-Making (MCDM) and Multi-Objective Optimization (MOO) Methods under Uncertainty to Facilitate Sustainability Assess," Sustainability, MDPI, vol. 16(7), pages 1-21, March.
    16. Konstantin Barkalov & Ilya Lebedev & Marina Usova & Daria Romanova & Daniil Ryazanov & Sergei Strijhak, 2022. "Optimization of Turbulence Model Parameters Using the Global Search Method Combined with Machine Learning," Mathematics, MDPI, vol. 10(15), pages 1-20, July.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:10:y:2022:i:11:p:1827-:d:824652. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.