基于模拟退火算法的Hopfield神经网络参数优化

Abstract

Abstract:

In order to solve the parameter setting problem during the application process of Hopfield neural network.The working principle of Hopfield neural network is described, the neural network model parameter selection problem in the TSP(Traveling Salesman Problem) problems solving process is analyed On the basis established the evaluation function of network by using normalized on output data, and then use simulated annealing algorithm to select the optimal parameters. The results show that, after optimization of parameters, Hopfield neural network can obtain the optimal solution of TSP problems more effective and more quickly.

Key words: parameter optimize, neural network, traveling salesman problem(TSP), simulated annealing

CLC Number:

TP301

QI Xiao-Gang, WANG Yun-He. Hopfield Neural Network Parameter Optimization Based on Simulated Annealing Algorithm[J].J4, 2011, 29(6): 585-589.

References

［1］王勇, 伍铁如, 马儒宁. 神经网络在二次规划问题中的应用［J］. 吉林大学学报：
理学版, 2008, 46(3): 448-452.
WANG Yong, WU Tie-ru, MA Ru-ning. Neural Network for Solving Quadratic Programming Problems ［J］. Journal of Jilin University：Science Edition, 2008, 46(3): 448-452.
［2］王怡雯, 丛爽. 用随机神经网络优化求解C-TSP ［J］. 吉林大学学报：信息科学版, 2004, 22(4): 359-363. 
WANG Yi-wen, CONG Shuang. Solving C-TSP With Random Neural Network ［J］. Journal of Jilin University：Information Science Edition, 2004, 22(4): 359-363.
［3］魏连伟, 邵景力, 张建立，等. 模拟退火算法反演水文地质参数算例研究［J］. 吉林大学学报：地球科学版, 2004, 34(4): 612-616. 
WEI Lian-wei, SHAO Jing-li, ZHANG Jian-li, et al. Application of Simulated Annealing Algorithm to Hydrogeological Parameter Inversion ［J］. Journal of Jilin Un
iversity：Earth Science Edition, 2004, 34(4): 612-616. 
［4］HOPFIELD J J.Neural Networks and Physical Systems with Emergent Collective Computational Abilities［J］.Proceedings of the National Academy of Sciences(USA),1982,79(8):2554-2558.
［5］LIU Rong, LIU Ze-min. Theories on Solving the Travelling Salesman Problem Based on Artificial Neural Network and Their Applications ［J］. The Journal of China Universities of Posts and Telecommunications, 1998 (1):78.
［6］张玉艳, 陈萍. Hopfield神经网络求解TSP中的参数分析［J］. 微电子学与计算机, 2003 (5): 8-10.
ZHANG Yu-yan, CHEN Ping. The Parameters Analysis in Using Hopfield NN to Solve the TSP ［J］. Microelectronics & Computer, 2003 (5): 8-10.
［7］姜国均. Hopfield网络解TSP的改进算法［J］. 浙江大学学报:理学版, 2011, 28(2): 160-163.JIANG Guo-jun. A Modified Algorithm of Hopfield Network to Solve TSP ［J］. Journal of Zhejiang University:Sciences Edition, 2011, 28(2): 160-163.
［8］徐力平,张炎华.评价神经网络拟合精度的另一个指标［J］.上海交通大学学报,2002,36(7):980-983.
XU Li-ping, ZHANG Yan-hua. Another Criterion to Judge Performance of Neural Networks［J］. Journal of Shanghai Jiaotong University, 2002,36(7):980-983.
［9］刘汉军, 段立松, 董永峰,等. 随机非对称Hopfield模型中恢复带性质研究［J］. 吉林大学学报：理学版, 2003, 41(1):81-84. 
LIU Han-jun, DUAN Li-song, DONG Yong-feng, et al. Studies of the Properties of the Retrieval Band of a Hopfield Model with Random Asymmetric Interactions ［J］.
Journal of Jilin University：Science Edition, 2003, 41(1): 81-84. 
［10］
[KG-*2]陈萍, 郭金锋. 对Hopfield神经网络求解TSP的研究［J］. 北京邮电大学学报, 1999, 22(2)：58-61.
CHEN Ping, GUO Jin-feng. Analysis on Hopfield Neural Networks Solution to TSP ［J］.Journal of Beijing University of Posts and Telecommunications, 1999, 22(2)：58-61.

[1]	MENG Chuannan，SUI Yang，ZHANG Jie，WANG Yue，DONG Wei，ZHANG Xindong，ＲUAN Shengping. Spectrum Feature Extraction Method Based on YSPSO-ＲBFN High-Precision Brillouin Scattering [J]. Journal of Jilin University(Information Science Ed, 2018, 36(4): 372-380.
[2]	ＲEN Weijian，SONG Yue，CHNE Jianling，ＲEN Lu，SUN Qinjiang. Steel Grade Identification Based on Improved Convolution Neural Network [J]. Journal of Jilin University(Information Science Ed, 2018, 36(3): 325-332.
[3]	LIU Fu，LIU Xing，KANG Bing. Gaze Estimation Algorithm Based on Shallow Ｒesidual Network [J]. Journal of Jilin University(Information Science Ed, 2018, 36(3): 333-338.
[4]	NI Hongmei,LIU Yongjian,LI Panchi . Prediction Method Based on Improved ABC Algorithm and RBF Neural Network [J]. Journal of Jilin University(Information Science Ed, 2018, 36(1): 78-84.
[5]	HUANG Sihui, CHEN Wanzhong, LI Jing. Network Intrusion Detection Based on Extreme Learning Machine and Principal Component Analysis [J]. Journal of Jilin University(Information Science Ed, 2017, 35(5): 576-583.
[6]	LI Xuegui,XU Shaohua,ZHAO Entao,ZHAO Ling . Reservoir Lithology Discrimination Based on LVQ Process Neural Network [J]. Journal of Jilin University(Information Science Ed, 2017, 35(4): 398-404.
[7]	YU Hong,CHENG Chao . Based on QoS Link Selection Algorithm of Many Constraints Feedback [J]. Journal of Jilin University(Information Science Ed, 2017, 35(3): 311-318.
[8]	REN Weijian,TIAN Yecen,ZHU Yongbo . Application of CS Neural Network in Pumping Units’Fault Diagnosis [J]. Journal of Jilin University(Information Science Ed, 2017, 35(3): 324-332.
[9]	WANG Zijian, WANG Dejun. Engine Misfire Diagnosis Based on Probabilistic Neural Network [J]. Journal of Jilin University(Information Science Ed, 2016, 34(2): 229-236.
[10]	WANG Dejun, WANG Xicong, DU Wantong. Vehicle Yaw Rate Estimation Using BP Neural Networks [J]. Journal of Jilin University(Information Science Ed, 2016, 34(1): 47-53.
[11]	WANG Ganggang, LIAO Qing, XU Yurui, LIU Le, HOU Alin. Hologram Compression Using BP Neural Network by Modified Particle Swarm Optimization [J]. Journal of Jilin University(Information Science Ed, 2016, 34(1): 147-151.
[12]	JIANG Yinling, LI Yanhui, WANG Haixing. Improved Neural Network State Observer Designed for Nonlinear System [J]. Journal of Jilin University(Information Science Ed, 2015, 33(4): 471-.
[13]	WANG Yanqin, REN Weijian, WANG Zhongyun. Application of Ant Colony Neural Network in Transformer Fault Diagnosis [J]. Journal of Jilin University(Information Science Ed, 2014, 32(6): 637-645.
[14]	WANG Qiong, WANG Lei, REN Weijian. Research on Estimating Parameters of Weibull Distribution Model Based on FPSO-SA [J]. Journal of Jilin University(Information Science Ed, 2014, 32(5): 476-483.
[15]	LU Huibin, WANG Lijia. Color Image Encryption Algorithm of Chaotic Based on the Hopfield Network [J]. Journal of Jilin University(Information Science Ed, 2014, 32(2): 131-137.

Hopfield Neural Network Parameter Optimization Based on Simulated Annealing Algorithm

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0