Particle Swarm Optimization Based Approach for Finding Optimal Values of Convolutional Neural Network Parameters

被引:23
作者
Sinha, Toshi [1 ]
Haidar, Ali [1 ]
Verma, Brijesh [1 ]
机构
[1] Cent Queensland Univ, Sch Engn & Technol, Ctr Intelligent Syst, Rockhampton, Qld, Australia
来源
2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) | 2018年
关键词
Convolutional Neural Networks; Optimization; Particle Swarm Optimization; Image Classification; CODED GENETIC ALGORITHM;
D O I
10.1109/CEC.2018.8477728
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Convolutional Neural Networks (CNNs) have demonstrated great potential in complex image classification problems in past few years. CNNs have a large number of parameters and the system accuracy depends directly on the selection of these parameters. With diverse parameters, selection of optimal parameter remains a trial and error, ad hoc or expert's mercy. In practice, optimal parameter selection remains the biggest obstacle in designing a real-world application using CNN. Convolutional neural network's performance is highly affected by its parameters. A novel approach is proposed in this paper to select convolutional neural network parameters in an image classification task. The proposed approach incorporated particle swarm optimization to select the parameters of the convolutional network. Two datasets, one benchmark CIFAR-10 and one real world application dataset, road-side vegetation dataset, were selected to evaluate the proposed approach. It is demonstrated that proposed approach efficiently explores the solution space, and determines the best combination of parameters. Extensive experiments, along with the statistical tests, revealed that proposed approach is an effective technique for automatically optimizing CNN's parameters.
引用
收藏
页码:1500 / 1505
页数:6
相关论文
共 50 条
[41]   Adaptive Inversion Control of Missile based on Neural Network and Particle Swarm Optimization [J].
Song, Shuzhong ;
Liang, Kun ;
Ma, Jianwei ;
Yang, Danfeng .
2012 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION AND LOGISTICS (ICAL), 2012, :30-34
[42]   Manipulator inverse kinematics control based on particle swarm optimization neural network [J].
Wen Xiulan ;
Sheng Danghong ;
Guo jing .
SEVENTH INTERNATIONAL SYMPOSIUM ON INSTRUMENTATION AND CONTROL TECHNOLOGY: OPTOELECTRONIC TECHNOLOGY AND INSTUMENTS, CONTROL THEORY AND AUTOMATION, AND SPACE EXPLORATION, 2008, 7129
[43]   Neural network predictive control based on particle swarm optimization for urban expressway [J].
Lu, Zhilin ;
Fan, Bingquan ;
Wang, Dongli ;
He, Xiaoyang .
WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS, 2006, :8606-+
[44]   An Improved PID Neural Network Control Algorithm Based on Particle Swarm Optimization [J].
Dou, Chunhong ;
Zhang, Ling .
2010 THE 3RD INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND INDUSTRIAL APPLICATION (PACIIA2010), VOL VI, 2010, :32-34
[45]   A ELEVATOR GROUP CONTROL METHOD BASED ON PARTICLE SWARM OPTIMIZATION AND NEURAL NETWORK [J].
Fu Guojiang .
2011 3RD INTERNATIONAL CONFERENCE ON COMPUTER TECHNOLOGY AND DEVELOPMENT (ICCTD 2011), VOL 2, 2012, :733-737
[46]   An Improved PID Neural Network Control Algorithm Based on Particle Swarm Optimization [J].
Dou, Chunhong ;
Zhang, Ling .
2011 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION AND INDUSTRIAL APPLICATION (ICIA2011), VOL I, 2011, :32-34
[47]   BP NEURAL NETWORK IN CLASSIFICATION OF FABRIC DEFECT BASED ON PARTICLE SWARM OPTIMIZATION [J].
Liu, Su-Yi ;
Zhang, Le-Duo ;
Wang, Qian ;
Liu, Jing-Jing .
PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION, VOLS 1 AND 2, 2008, :216-220
[48]   Application of Particle Swarm Optimization Based on Neural Network for Artillery Range Prediction [J].
Chen, Y. W. ;
Lee, Y. -L. ;
Kung, C. -C. .
CONTROL ENGINEERING AND APPLIED INFORMATICS, 2014, 16 (04) :73-80
[49]   Particle swarm optimization based Probabilistic Neural Network for power transformer protection [J].
Tripathy, Manoj ;
Maheshwari, R. P. ;
Verma, H. K. .
2006 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY, VOLS 1-6, 2006, :252-+
[50]   Particle swarm optimization for construction of neural network-based prediction intervals [J].
Quan, Hao ;
Srinivasan, Dipti ;
Khosravi, Abbas .
NEUROCOMPUTING, 2014, 127 :172-180