Research on image classification model based on deep convolution neural network
Abstract Based on the analysis of the error backpropagation algorithm, we propose an innovative training criterion of depth neural network for maximum interval minimum classification error. At the same time, the cross entropy and M3CE are analyzed and combined to obtain better results. Finally, we t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2019-02-01
|
Series: | EURASIP Journal on Image and Video Processing |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13640-019-0417-8 |
_version_ | 1811209047924277248 |
---|---|
author | Mingyuan Xin Yong Wang |
author_facet | Mingyuan Xin Yong Wang |
author_sort | Mingyuan Xin |
collection | DOAJ |
description | Abstract Based on the analysis of the error backpropagation algorithm, we propose an innovative training criterion of depth neural network for maximum interval minimum classification error. At the same time, the cross entropy and M3CE are analyzed and combined to obtain better results. Finally, we tested our proposed M3 CE-CEc on two deep learning standard databases, MNIST and CIFAR-10. The experimental results show that M3 CE can enhance the cross-entropy, and it is an effective supplement to the cross-entropy criterion. M3 CE-CEc has obtained good results in both databases. |
first_indexed | 2024-04-12T04:31:41Z |
format | Article |
id | doaj.art-c9096d4dfc954d3186bea00e53f38c85 |
institution | Directory Open Access Journal |
issn | 1687-5281 |
language | English |
last_indexed | 2024-04-12T04:31:41Z |
publishDate | 2019-02-01 |
publisher | SpringerOpen |
record_format | Article |
series | EURASIP Journal on Image and Video Processing |
spelling | doaj.art-c9096d4dfc954d3186bea00e53f38c852022-12-22T03:47:55ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812019-02-012019111110.1186/s13640-019-0417-8Research on image classification model based on deep convolution neural networkMingyuan Xin0Yong Wang1School of Computer and Information Engineering, Heihe UniversityHeihe UniversityAbstract Based on the analysis of the error backpropagation algorithm, we propose an innovative training criterion of depth neural network for maximum interval minimum classification error. At the same time, the cross entropy and M3CE are analyzed and combined to obtain better results. Finally, we tested our proposed M3 CE-CEc on two deep learning standard databases, MNIST and CIFAR-10. The experimental results show that M3 CE can enhance the cross-entropy, and it is an effective supplement to the cross-entropy criterion. M3 CE-CEc has obtained good results in both databases.http://link.springer.com/article/10.1186/s13640-019-0417-8Convolution neural networkImage classificationM3CE-CEc |
spellingShingle | Mingyuan Xin Yong Wang Research on image classification model based on deep convolution neural network EURASIP Journal on Image and Video Processing Convolution neural network Image classification M3CE-CEc |
title | Research on image classification model based on deep convolution neural network |
title_full | Research on image classification model based on deep convolution neural network |
title_fullStr | Research on image classification model based on deep convolution neural network |
title_full_unstemmed | Research on image classification model based on deep convolution neural network |
title_short | Research on image classification model based on deep convolution neural network |
title_sort | research on image classification model based on deep convolution neural network |
topic | Convolution neural network Image classification M3CE-CEc |
url | http://link.springer.com/article/10.1186/s13640-019-0417-8 |
work_keys_str_mv | AT mingyuanxin researchonimageclassificationmodelbasedondeepconvolutionneuralnetwork AT yongwang researchonimageclassificationmodelbasedondeepconvolutionneuralnetwork |