IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v12y2024i24p3982-d1546850.html
   My bibliography  Save this article

Integral Neuron: A New Concept for Nonlinear Neuron Modeling Using Weight Functions. Creation of XOR Neurons

Author

Listed:
  • Kostadin Yotov

    (Faculty of Mathematics and Informatics, University of Plovdiv Paisii Hilendarski, 236 Bulgaria Blvd., 4027 Plovdiv, Bulgaria)

  • Emil Hadzhikolev

    (Faculty of Mathematics and Informatics, University of Plovdiv Paisii Hilendarski, 236 Bulgaria Blvd., 4027 Plovdiv, Bulgaria)

  • Stanka Hadzhikoleva

    (Faculty of Mathematics and Informatics, University of Plovdiv Paisii Hilendarski, 236 Bulgaria Blvd., 4027 Plovdiv, Bulgaria)

Abstract

In the present study, an extension of the idea of dynamic neurons is proposed by replacing the weights with a weight function that is applied simultaneously to all neuron inputs. A new type of artificial neuron called an integral neuron is modeled, in which the total signal is obtained as the integral of the weight function. The integral neuron enhances traditional neurons by allowing the signal shape to be linear and nonlinear. The training of the integral neuron involves finding the parameters of the weight function, where its functional values directly influence the total signal in the neuron’s body. This article presents theoretical and experimental evidence for the applicability and convergence of standard training methods such as gradient descent, Gauss–Newton, and Levenberg–Marquardt in searching for the optimal weight function of an integral neuron. The experimental part of the study demonstrates that a single integral neuron can be trained on the logical XOR function—something that is impossible for single classical neurons due to the linear nature of the summation in their bodies.

Suggested Citation

  • Kostadin Yotov & Emil Hadzhikolev & Stanka Hadzhikoleva, 2024. "Integral Neuron: A New Concept for Nonlinear Neuron Modeling Using Weight Functions. Creation of XOR Neurons," Mathematics, MDPI, vol. 12(24), pages 1-44, December.
    • Handle: RePEc:gam:jmathe:v:12:y:2024:i:24:p:3982-:d:1546850
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/12/24/3982/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/12/24/3982/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Hu, Huanling & Wang, Lin & Tao, Rui, 2021. "Wind speed forecasting based on variational mode decomposition and improved echo state network," Renewable Energy, Elsevier, vol. 164(C), pages 729-751.
    2. Gao, Ruobin & Li, Ruilin & Hu, Minghui & Suganthan, Ponnuthurai Nagaratnam & Yuen, Kum Fai, 2023. "Dynamic ensemble deep echo state network for significant wave height forecasting," Applied Energy, Elsevier, vol. 329(C).
    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. Zhang, Yagang & Wang, Hui & Wang, Jingchao & Cheng, Xiaodan & Wang, Tong & Zhao, Zheng, 2024. "Ensemble optimization approach based on hybrid mode decomposition and intelligent technology for wind power prediction system," Energy, Elsevier, vol. 292(C).
    2. Tian, Zhongda & Chen, Hao, 2021. "Multi-step short-term wind speed prediction based on integrated multi-model fusion," Applied Energy, Elsevier, vol. 298(C).
    3. Acikgoz, Hakan & Budak, Umit & Korkmaz, Deniz & Yildiz, Ceyhun, 2021. "WSFNet: An efficient wind speed forecasting model using channel attention-based densely connected convolutional neural network," Energy, Elsevier, vol. 233(C).
    4. Eduardo Luiz Alba & Gilson Adamczuk Oliveira & Matheus Henrique Dal Molin Ribeiro & Érick Oliveira Rodrigues, 2024. "Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations," Forecasting, MDPI, vol. 6(3), pages 1-25, September.
    5. Elianne Mora & Jenny Cifuentes & Geovanny Marulanda, 2021. "Short-Term Forecasting of Wind Energy: A Comparison of Deep Learning Frameworks," Energies, MDPI, vol. 14(23), pages 1-26, November.
    6. Shengxiang Lv & Lin Wang & Sirui Wang, 2023. "A Hybrid Neural Network Model for Short-Term Wind Speed Forecasting," Energies, MDPI, vol. 16(4), pages 1-18, February.
    7. Xiang Ying & Keke Zhao & Zhiqiang Liu & Jie Gao & Dongxiao He & Xuewei Li & Wei Xiong, 2022. "Wind Speed Prediction via Collaborative Filtering on Virtual Edge Expanding Graphs," Mathematics, MDPI, vol. 10(11), pages 1-16, June.
    8. Kuznetsov, G.V. & Syrodoy, S.V. & Nigay, N.A. & Maksimov, V.I. & Gutareva, N.Yu., 2021. "Features of the processes of heat and mass transfer when drying a large thickness layer of wood biomass," Renewable Energy, Elsevier, vol. 169(C), pages 498-511.
    9. Bai, Yulong & Liu, Ming-De & Ding, Lin & Ma, Yong-Jie, 2021. "Double-layer staged training echo-state networks for wind speed prediction using variational mode decomposition," Applied Energy, Elsevier, vol. 301(C).
    10. Lu Peng & Sheng‐Xiang Lv & Lin Wang, 2024. "Explainable machine learning techniques based on attention gate recurrent unit and local interpretable model‐agnostic explanations for multivariate wind speed forecasting," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 43(6), pages 2064-2087, September.
    11. Zheng, Zihao & Ali, Mumtaz & Jamei, Mehdi & Xiang, Yong & Abdulla, Shahab & Yaseen, Zaher Mundher & Farooque, Aitazaz A., 2023. "Multivariate data decomposition based deep learning approach to forecast one-day ahead significant wave height for ocean energy generation," Renewable and Sustainable Energy Reviews, Elsevier, vol. 185(C).
    12. Luis Lopez & Ingrid Oliveros & Luis Torres & Lacides Ripoll & Jose Soto & Giovanny Salazar & Santiago Cantillo, 2020. "Prediction of Wind Speed Using Hybrid Techniques," Energies, MDPI, vol. 13(23), pages 1-13, November.
    13. Wu, Han & Gao, Xiao-Zhi & Heng, Jia-Ni, 2024. "Bio-multisensory-inspired gate-attention coordination model for forecasting short-term significant wave height," Energy, Elsevier, vol. 294(C).
    14. Cai, Chenhao & Zhang, Leyao & Zhou, Jianguo, 2024. "DMPR: A novel wind speed forecasting model based on optimized decomposition, multi-objective feature selection, and patch-based RNN," Energy, Elsevier, vol. 310(C).
    15. Wu, Chunying & Wang, Jianzhou & Hao, Yan, 2022. "Deterministic and uncertainty crude oil price forecasting based on outlier detection and modified multi-objective optimization algorithm," Resources Policy, Elsevier, vol. 77(C).
    16. Javad Saadat & Mohsen Farshad & Hussein Eliasi, 2023. "Optimizing Structure and Internal Unit Weights of Echo State Network for an Efficient LMS-Based Online Training," SN Operations Research Forum, Springer, vol. 4(1), pages 1-14, March.
    17. Xiaoou Li & Yingqin Zhu, 2024. "Neural Networks with Transfer Learning and Frequency Decomposition for Wind Speed Prediction with Missing Data," Mathematics, MDPI, vol. 12(8), pages 1-20, April.
    18. Zhang, Chu & Li, Zhengbo & Ge, Yida & Liu, Qianlong & Suo, Leiming & Song, Shihao & Peng, Tian, 2024. "Enhancing short-term wind speed prediction based on an outlier-robust ensemble deep random vector functional link network with AOA-optimized VMD," Energy, Elsevier, vol. 296(C).
    19. Zhang, Yagang & Zhao, Yunpeng & Shen, Xiaoyu & Zhang, Jinghui, 2022. "A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms," Applied Energy, Elsevier, vol. 305(C).
    20. Lu, Peng & Ye, Lin & Zhao, Yongning & Dai, Binhua & Pei, Ming & Tang, Yong, 2021. "Review of meta-heuristic algorithms for wind power prediction: Methodologies, applications and challenges," Applied Energy, Elsevier, vol. 301(C).

    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:12:y:2024:i:24:p:3982-:d:1546850. 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.