Author(s): Ning, X (Ning, Xin); Tian, WJ (Tian, Weijuan); Yu, ZY (Yu, Zaiyang); Li, WJ (Li, Weijun); Bai, X (Bai, Xiao); Wang, YB (Wang, Yuebao)

Source: PATTERN RECOGNITION Volume: 131 Article Number: 108873 DOI: 10.1016/j.patcog.2022.108873 Published: NOV 2022

Abstract: Recent advances in deep neural networks (DNNs) have mainly focused on innovations in network ar-chitecture and loss function. In this paper, we introduce a flexible high-order coverage function (HCF) neuron model to replace the fully-connected (FC) layers. The approximation theorem and proof for the HCF are also presented to demonstrate its fitting ability. Unlike the FC layers, which cannot handle high-dimensional data well, the HCF utilizes weight coefficients and hyper-parameters to mine under-lying geometries with arbitrary shapes in an n-dimensional space. To explore the power and poten-tial of our HCF neuron model, a high-order coverage function neural network (HCFNN) is proposed, which incorporates the HCF neuron as the building block. Moreover, a novel adaptive optimization method for weights and hyper-parameters is designed to achieve effective network learning. Compre-hensive experiments on nine datasets in several domains validate the effectiveness and generalizability of the HCF and HCFNN. The proposed method provides a new perspective for further developments in DNNs and ensures wide application in the field of image classification. The source code is available at https://github.com/Tough2011/HCFNet.git (c) 2022 Elsevier Ltd. All rights reserved.

Accession Number: WOS:000841964700003

ISSN: 0031-3203

eISSN: 1873-5142

Full Text: https://www.sciencedirect.com/science/article/pii/S0031320322003545?via%3Dihub