Image retrieval based on fireworks algorithm optimizing convolutional neural network

被引：0

作者：

Wang, Chunzhi ^{[1
]}

Wu, Pan ^{[1
]}

Yan, Lingyu ^{[1
]}

Zhou, Fangyu ^{[1
]}

Cai, Wencheng ^{[1
]}

机构：

[1] Hubei Univ Technol, Sch Comp Sci, Wuhan, Hubei, Peoples R China

来源：

PROCEEDINGS OF THE 2018 IEEE 4TH INTERNATIONAL SYMPOSIUM ON WIRELESS SYSTEMS WITHIN THE INTERNATIONAL CONFERENCES ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS (IDAACS-SWS) | 2018年

基金：

中国国家自然科学基金;

关键词：

fireworks algorithm; convolutional neural network; gradient descent; image retrieval;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

For the problem of the slow convergence rate of the traditional CNN algorithm using gradient descent algorithm to optimize parameters, a CNN model based on fireworks algorithm optimization is proposed, the parameters that need to be optimized are used as the input to the fireworks algorithm, and the cross-entropy (error) is used as the fitness function to improve the tuning process in the backward propagation, the MNIST handwritten character set is used for simulation experiments of image retrieval. The results show that the convergence speed of the improved algorithm is significantly improved.

引用

页码：53 / 56

页数：4

共 18 条

[1] A Framework for Designing the Architectures of Deep Convolutional Neural Networks
Albelwi, Saleh
Mahmood, Ausif
[J]. ENTROPY, 2017, 19 (06)
[2] [Anonymous], 2015, Fireworks Algorithm
[3] [Anonymous], INT J SYSTEM ASSURAN
[4] [Anonymous], 2014, Learning and transferring mid-level image representations using convolutional neural networks. pages
[5] [Anonymous], 2015, COMPUTER SCI
[6] [Anonymous], 1990, Advances in neural information processing systems
[7] [Anonymous], COMP VIS PATT REC 19
[8] [Anonymous], MEMETIC COMPUTING
[9] Ayumi V, 2016, INT C ADV COMP SCI I, P506, DOI 10.1109/ICACSIS.2016.7872787
[10] Ciresan D, 2012, PROC CVPR IEEE, P3642, DOI 10.1109/CVPR.2012.6248110

← 1 2 →