IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i3p494-d741782.html
   My bibliography  Save this article

Local Linear Approximation Algorithm for Neural Network

Author

Listed:
  • Mudong Zeng

    (Department of Statistics, Pennsylvania State University, University Park, PA 16802, USA
    These authors contributed equally to this work.)

  • Yujie Liao

    (Department of Statistics, Pennsylvania State University, University Park, PA 16802, USA
    These authors contributed equally to this work.)

  • Runze Li

    (Department of Statistics, Pennsylvania State University, University Park, PA 16802, USA)

  • Agus Sudjianto

    (Corporate Model Risk, Wells Fargo Bank, Charlotte, NC 28202, USA)

Abstract

This paper aims to develop a new training strategy to improve efficiency in estimation of weights and biases in a feedforward neural network (FNN). We propose a local linear approximation (LLA) algorithm, which approximates ReLU with a linear function at the neuron level and estimate the weights and biases of one-hidden-layer neural network iteratively. We further propose the layer-wise optimized adaptive neural network (LOAN), in which we use the LLA to estimate the weights and biases in the LOAN layer by layer adaptively. We compare the performance of the LLA with the commonly-used procedures in machine learning based on seven benchmark data sets. The numerical comparison implies that the proposed algorithm may outperform the existing procedures in terms of both training time and prediction accuracy.

Suggested Citation

  • Mudong Zeng & Yujie Liao & Runze Li & Agus Sudjianto, 2022. "Local Linear Approximation Algorithm for Neural Network," Mathematics, MDPI, vol. 10(3), pages 1-22, February.
    • Handle: RePEc:gam:jmathe:v:10:y:2022:i:3:p:494-:d:741782
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/3/494/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/10/3/494/
    Download Restriction: no
    ---><---

    Citations

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


    Cited by:

    1. Joaquim Fernando Pinto da Costa & Manuel Cabral, 2022. "Statistical Methods with Applications in Data Mining: A Review of the Most Recent Works," Mathematics, MDPI, vol. 10(6), pages 1-22, March.

    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:3:p:494-:d:741782. 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.