IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v9y2021i21p2705-d664087.html
   My bibliography  Save this article

Performance of a Novel Chaotic Firefly Algorithm with Enhanced Exploration for Tackling Global Optimization Problems: Application for Dropout Regularization

Author

Listed:
  • Nebojsa Bacanin

    (Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia)

  • Ruxandra Stoean

    (Romanian Institute of Science and Technology, Str. Virgil Fulicea 3, 400022 Cluj-Napoca, Romania)

  • Miodrag Zivkovic

    (Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia)

  • Aleksandar Petrovic

    (Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia)

  • Tarik A. Rashid

    (Computer Science and Engineering, University of Kurdistan Hewler, 30 Meter Avenue, Erbil 44001, Iraq)

  • Timea Bezdan

    (Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia)

Abstract

Swarm intelligence techniques have been created to respond to theoretical and practical global optimization problems. This paper puts forward an enhanced version of the firefly algorithm that corrects the acknowledged drawbacks of the original method, by an explicit exploration mechanism and a chaotic local search strategy. The resulting augmented approach was theoretically tested on two sets of bound-constrained benchmark functions from the CEC suites and practically validated for automatically selecting the optimal dropout rate for the regularization of deep neural networks. Despite their successful applications in a wide spectrum of different fields, one important problem that deep learning algorithms face is overfitting. The traditional way of preventing overfitting is to apply regularization; the first option in this sense is the choice of an adequate value for the dropout parameter. In order to demonstrate its ability in finding an optimal dropout rate, the boosted version of the firefly algorithm has been validated for the deep learning subfield of convolutional neural networks, with respect to five standard benchmark datasets for image processing: MNIST, Fashion-MNIST, Semeion, USPS and CIFAR-10. The performance of the proposed approach in both types of experiments was compared with other recent state-of-the-art methods. To prove that there are significant improvements in results, statistical tests were conducted. Based on the experimental data, it can be concluded that the proposed algorithm clearly outperforms other approaches.

Suggested Citation

  • Nebojsa Bacanin & Ruxandra Stoean & Miodrag Zivkovic & Aleksandar Petrovic & Tarik A. Rashid & Timea Bezdan, 2021. "Performance of a Novel Chaotic Firefly Algorithm with Enhanced Exploration for Tackling Global Optimization Problems: Application for Dropout Regularization," Mathematics, MDPI, vol. 9(21), pages 1-33, October.
  • Handle: RePEc:gam:jmathe:v:9:y:2021:i:21:p:2705-:d:664087
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/9/21/2705/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/9/21/2705/
    Download Restriction: no
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Dušan S. Radivojević & Ivan M. Lazović & Nikola S. Mirkov & Uzahir R. Ramadani & Dušan P. Nikezić, 2023. "A Comparative Evaluation of Self-Attention Mechanism with ConvLSTM Model for Global Aerosol Time Series Forecasting," Mathematics, MDPI, vol. 11(7), pages 1-13, April.
    2. Luka Jovanovic & Dejan Jovanovic & Nebojsa Bacanin & Ana Jovancai Stakic & Milos Antonijevic & Hesham Magd & Ravi Thirumalaisamy & Miodrag Zivkovic, 2022. "Multi-Step Crude Oil Price Prediction Based on LSTM Approach Tuned by Salp Swarm Algorithm with Disputation Operator," Sustainability, MDPI, vol. 14(21), pages 1-29, November.
    3. Tao Xu & Zeng Gao & Yi Zhuang, 2023. "Fault Prediction of Control Clusters Based on an Improved Arithmetic Optimization Algorithm and BP Neural Network," Mathematics, MDPI, vol. 11(13), pages 1-28, June.
    4. Zaid Bin Mushtaq & Shoaib Mohd Nasti & Chaman Verma & Maria Simona Raboaca & Neerendra Kumar & Samiah Jan Nasti, 2022. "Super Resolution for Noisy Images Using Convolutional Neural Networks," Mathematics, MDPI, vol. 10(5), pages 1-18, February.
    5. Marco Boresta & Diego Maria Pinto & Giuseppe Stecca, 2024. "Bridging operations research and machine learning for service cost prediction in logistics and service industries," Annals of Operations Research, Springer, vol. 342(1), pages 113-139, November.

    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:9:y:2021:i:21:p:2705-:d:664087. 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.

    We have no bibliographic references for this item. You can help adding them by using 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.