Research on PSO algorithm in neural network generalization

doi:10.3778/j.issn.1002-8331.2009.29.010

Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (29): 34-36.DOI: 10.3778/j.issn.1002-8331.2009.29.010

• 研究、探讨 • Previous Articles Next Articles

Research on PSO algorithm in neural network generalization

LIU Jun¹，QIU Xiao-hong^1，2，WANG Zhi-yong¹，YANG Peng¹

1.College of Computer，Jiangxi Normal University，Nanchang 330022，China
2.School of Software，Jiangxi Agricultural University，Nanchang 330045，China

Received:2008-11-12 Revised:2009-02-05 Online:2009-10-11 Published:2009-10-11
Contact: LIU Jun

PSO粒子群算法在神经网络泛化能力中研究

刘军¹，邱晓红^1，2，汪志勇¹，杨鹏¹

1.江西师范大学计算机学院，南昌 330022
2.江西农业大学软件学院，南昌 330045

通讯作者: 刘军

Abstract

Abstract: This paper employs the PSO algorithm to update the weights，the biases and the transfer function’s coefficients of the hidden layer in the neural network.As to the phenomena of good approximation and bad generalization，the MSE of the training set and the MSW of the weights are integrated into the fitness goal.In the experiment，the GPSO-BP algorithm which optimizes the coefficients of the transfer function and has the small weights and thresholds is better than the BP algorithm and the PSO-BP algorithm in terms of the mean correct recognition and the stability.

Key words: Back Propagation（BP） neural network, Particle Swarm Optimization（PSO） algorithm, transfer function, approximation, generalization

摘要： 利用PSO粒子群算法对神经网络的权值和阈值，隐藏层中神经元的传递函数系数进行优化。针对网络训练效果好，而泛化能力很差的情况，将训练样本均方差和权值的平方和结合作为PSO算法的目标函数。实验表明，该方法比惯性权值PSO-BP算法和基本梯度下降法好，不但稳定性好，而且预测精度高，泛化能力得到明显加强。

关键词: BP网络, PSO粒子群算法, 传递函数, 逼近, 泛化

CLC Number:

TP131

LIU Jun¹，QIU Xiao-hong^1，2，WANG Zhi-yong¹，YANG Peng¹. Research on PSO algorithm in neural network generalization[J]. Computer Engineering and Applications, 2009, 45(29): 34-36.

刘军¹，邱晓红^1，2，汪志勇¹，杨鹏¹. PSO粒子群算法在神经网络泛化能力中研究[J]. 计算机工程与应用, 2009, 45(29): 34-36.

[1]	DENG Lifang, DANG Jianwu, WANG Yangping, WANG Song. Steganalysis of Spatial Image Based on Hybrid Kernel Feature Mapping [J]. Computer Engineering and Applications, 2021, 57(9): 118-125.
[2]	WANG Jiayue, SHI Li. Research on Path Optimization and Charging Strategy of Electric Refrigerated Vehicle Considering Cost of Battery Capacity Degradation [J]. Computer Engineering and Applications, 2021, 57(24): 283-289.
[3]	MENG Xiangfu, WANG Dandan, ZHANG Feng. Overview of Spatial Keyword Queries [J]. Computer Engineering and Applications, 2021, 57(20): 13-24.
[4]	YANG Yong, GUO Ling, YE Yangdong. Approach of Total Variation Flow Boundary Integrated with M2GGD for Natural Image Segmentation [J]. Computer Engineering and Applications, 2021, 57(11): 202-210.
[5]	LIAO Weilin, CHENG Shan, SHANG Dongdong, WEI Zhaobin. Particle Swarm Optimization Algorithm Integrated with Multiple-Strategies [J]. Computer Engineering and Applications, 2021, 57(1): 69-76.
[6]	YANG Geying, SHEN Xiajiong, SHI Xianjin, ZHANG Lei. Visualization of Association Rules in Context of Concept Lattices [J]. Computer Engineering and Applications, 2021, 57(1): 84-91.
[7]	HUO Lin, LU Yinli. Improved Particle Swarm Optimization for Android Malware Detection [J]. Computer Engineering and Applications, 2020, 56(7): 96-101.
[8]	MOU En, ZHANG Xianyong, YAO Yuesong, DENG Qie. Class-Specific Attribute Reduct and Its Heuristic Algorithm of Neighborhood Approximation Condition-Entropy [J]. Computer Engineering and Applications, 2020, 56(24): 175-180.
[9]	FAN Chunlong, HE Yufeng, WANG Yixin. Large Weight Suppression Strategy for Training Convolutional Neural Networks [J]. Computer Engineering and Applications, 2020, 56(2): 115-119.
[10]	SI Yanna, PU Jiexin, ZANG Shaofei. Neural Network Q Learning Algorithm Based on Residual Gradient Method [J]. Computer Engineering and Applications, 2020, 56(18): 137-142.
[11]	LI Zenggang, WANG Zhengyan, SUN Jingcheng. Research and Design of Handwritten Digital BP Neural Network Based on FPGA [J]. Computer Engineering and Applications, 2020, 56(17): 251-257.
[12]	TU Chunmei, CHEN Guobin, LIU Chao. Dark-Pixel-Prior Blind Deblurring Method [J]. Computer Engineering and Applications, 2020, 56(10): 213-219.
[13]	QIN Xiaoyan. Quasi-Truth Degree of First-Order Formula After Using Generalization Rule [J]. Computer Engineering and Applications, 2019, 55(6): 39-41.
[14]	QI Meilan, LI Xiaonan. Matroidal Structure Based on Set-Valued Mapping and Its Relationship with Covering Rough Sets [J]. Computer Engineering and Applications, 2019, 55(6): 50-56.
[15]	GUAN Wei1, ZHANG Lei2. PSO Attributes Clustering for Preserving Location Privacy [J]. Computer Engineering and Applications, 2019, 55(5): 96-104.

Research on PSO algorithm in neural network generalization

PSO粒子群算法在神经网络泛化能力中研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics