Research on improved convolutional wavelet neural network

Abstract Artificial neural networks (ANN) which include deep learning neural networks (DNN) have problems such as the local minimal problem of Back propagation neural network (BPNN), the unstable problem of Radial basis function neural network (RBFNN) and the limited maximum precision problem of Con...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jingwei Liu, Peixuan Li, Xuehan Tang, Jiaxin Li, Jiaming Chen
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/73398491843d4b05a4c5f1313fcd6564
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:73398491843d4b05a4c5f1313fcd6564
record_format dspace
spelling oai:doaj.org-article:73398491843d4b05a4c5f1313fcd65642021-12-02T19:12:27ZResearch on improved convolutional wavelet neural network10.1038/s41598-021-97195-62045-2322https://doaj.org/article/73398491843d4b05a4c5f1313fcd65642021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97195-6https://doaj.org/toc/2045-2322Abstract Artificial neural networks (ANN) which include deep learning neural networks (DNN) have problems such as the local minimal problem of Back propagation neural network (BPNN), the unstable problem of Radial basis function neural network (RBFNN) and the limited maximum precision problem of Convolutional neural network (CNN). Performance (training speed, precision, etc.) of BPNN, RBFNN and CNN are expected to be improved. Main works are as follows: Firstly, based on existing BPNN and RBFNN, Wavelet neural network (WNN) is implemented in order to get better performance for further improving CNN. WNN adopts the network structure of BPNN in order to get faster training speed. WNN adopts the wavelet function as an activation function, whose form is similar to the radial basis function of RBFNN, in order to solve the local minimum problem. Secondly, WNN-based Convolutional wavelet neural network (CWNN) method is proposed, in which the fully connected layers (FCL) of CNN is replaced by WNN. Thirdly, comparative simulations based on MNIST and CIFAR-10 datasets among the discussed methods of BPNN, RBFNN, CNN and CWNN are implemented and analyzed. Fourthly, the wavelet-based Convolutional Neural Network (WCNN) is proposed, where the wavelet transformation is adopted as the activation function in Convolutional Pool Neural Network (CPNN) of CNN. Fifthly, simulations based on CWNN are implemented and analyzed on the MNIST dataset. Effects are as follows: Firstly, WNN can solve the problems of BPNN and RBFNN and have better performance. Secondly, the proposed CWNN can reduce the mean square error and the error rate of CNN, which means CWNN has better maximum precision than CNN. Thirdly, the proposed WCNN can reduce the mean square error and the error rate of CWNN, which means WCNN has better maximum precision than CWNN.Jingwei LiuPeixuan LiXuehan TangJiaxin LiJiaming ChenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jingwei Liu
Peixuan Li
Xuehan Tang
Jiaxin Li
Jiaming Chen
Research on improved convolutional wavelet neural network
description Abstract Artificial neural networks (ANN) which include deep learning neural networks (DNN) have problems such as the local minimal problem of Back propagation neural network (BPNN), the unstable problem of Radial basis function neural network (RBFNN) and the limited maximum precision problem of Convolutional neural network (CNN). Performance (training speed, precision, etc.) of BPNN, RBFNN and CNN are expected to be improved. Main works are as follows: Firstly, based on existing BPNN and RBFNN, Wavelet neural network (WNN) is implemented in order to get better performance for further improving CNN. WNN adopts the network structure of BPNN in order to get faster training speed. WNN adopts the wavelet function as an activation function, whose form is similar to the radial basis function of RBFNN, in order to solve the local minimum problem. Secondly, WNN-based Convolutional wavelet neural network (CWNN) method is proposed, in which the fully connected layers (FCL) of CNN is replaced by WNN. Thirdly, comparative simulations based on MNIST and CIFAR-10 datasets among the discussed methods of BPNN, RBFNN, CNN and CWNN are implemented and analyzed. Fourthly, the wavelet-based Convolutional Neural Network (WCNN) is proposed, where the wavelet transformation is adopted as the activation function in Convolutional Pool Neural Network (CPNN) of CNN. Fifthly, simulations based on CWNN are implemented and analyzed on the MNIST dataset. Effects are as follows: Firstly, WNN can solve the problems of BPNN and RBFNN and have better performance. Secondly, the proposed CWNN can reduce the mean square error and the error rate of CNN, which means CWNN has better maximum precision than CNN. Thirdly, the proposed WCNN can reduce the mean square error and the error rate of CWNN, which means WCNN has better maximum precision than CWNN.
format article
author Jingwei Liu
Peixuan Li
Xuehan Tang
Jiaxin Li
Jiaming Chen
author_facet Jingwei Liu
Peixuan Li
Xuehan Tang
Jiaxin Li
Jiaming Chen
author_sort Jingwei Liu
title Research on improved convolutional wavelet neural network
title_short Research on improved convolutional wavelet neural network
title_full Research on improved convolutional wavelet neural network
title_fullStr Research on improved convolutional wavelet neural network
title_full_unstemmed Research on improved convolutional wavelet neural network
title_sort research on improved convolutional wavelet neural network
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/73398491843d4b05a4c5f1313fcd6564
work_keys_str_mv AT jingweiliu researchonimprovedconvolutionalwaveletneuralnetwork
AT peixuanli researchonimprovedconvolutionalwaveletneuralnetwork
AT xuehantang researchonimprovedconvolutionalwaveletneuralnetwork
AT jiaxinli researchonimprovedconvolutionalwaveletneuralnetwork
AT jiamingchen researchonimprovedconvolutionalwaveletneuralnetwork
_version_ 1718377051851849728