Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《中国化学工程学报(英文版)》 2012-06
Add to Favorite Get Latest Update

Fast Learning in Spiking Neural Networks by Learning Rate Adaptation

FANG Huijuan, LUO Jiliang and WANG Fei College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China  
For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.
【Fund】: Supported by the National Natural Science Foundation of China (60904018 61203040);; the Natural Science Foundation of Fujian Province of China (2009J05147 2011J01352);; the Foundation for Distinguished Young Scholars of Higher Education of Fujian Province of China (JA10004);; the Science Research Foundation of Huaqiao University (09BS617)
【CateGory Index】: TP183
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【References】
Chinese Journal Full-text Database 1 Hits
1 LIN Xiang-hong;WANG Xiang-wen;ZHANG Ning;MA Hui-fang;School of Computer Science and Engineering,Northwest Normal University;;Supervised Learning Algorithms for Spiking Neural Networks: A Review[J];电子学报;2015-03
【Citations】
Chinese Journal Full-text Database 3 Hits
1 Juan A. Lazzús Department of Physics, University of La Serena, Casilla 554, La Serena, Chile;Prediction of Flash Point Temperature of Organic Compounds Using a Hybrid Method of Group Contribution + Neural Network + Particle Swarm Optimization[J];Chinese Journal of Chemical Engineering;2010-05
2 Lü Ning,YU Xiaoyang(School of Automation,Harbin University of Science and Technology,Harbin 150080,Heilongjiang,China);Fault diagnosis in TE process based on feature selection via second order mutual information[J];化工学报;2009-09
3 ZOU Zhiyun 1,2, YU Dehong 2, FENG Wenqiang 2, YU Luping 2 and GUO Ning 2 1 School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China 2 Beijing Research Institute of Pharmaceutical Chemistry, Beijing 102205, China;An Intelligent Neural Networks System for Adaptive Learning and Prediction of a Bioreactor Benchmark Process[J];Chinese Journal of Chemical Engineering;2008-01
【Co-citations】
Chinese Journal Full-text Database 10 Hits
1 XU Yuan;LU Yushuai;CAI Yi;College of Information Science & Technology,Beijing University of Chemical Technology;;Multiple timing-driven based extreme learning machine whole process fault prediction and its application[J];化工学报;2015-01
2 Qunxiong Zhu;Yiwen Jia;Di Peng;Yuan Xu;College of Information Science and Technology, Beijing University of Chemical Technology;;Study and Application of Fault Prediction Methods with Improved Reservoir Neural Networks[J];Chinese Journal of Chemical Engineering;2014-07
3 XU Yuan;LIU Ying;ZHU Qunxiong;School of Information Science &Technology,Beijing University of Chemical Technology;;A complex process fault prognosis approach based on multivariate delayed sequences[J];化工学报;2013-12
4 ZHAO Xiaoqiang;XUE Yongfei;College of Electrical Engineering and Information Engineering,Lanzhou University of Technology;Technology & Research Center of Gansu Manufacturing Information Engineering;;Fault detect algorithm of chemical process based on kernel T-PLS[J];化工学报;2013-12
5 Tang Yongbo1,2,Gui Weihua1,Peng Tao1,Ouyang Wei3(1.School of Information Science and Engineering,Central South University,Changsha 410083,China;2.School of Physical Science and Engineering,Yichun University,Yichun 336000,China;3.China Nerin Engineering Co.,Ltd,Nanchang 330002,China);Prediction method for dissolved gas concentration in transformer oil based on variable selection of mutual information[J];仪器仪表学报;2013-07
6 Mehdi Bagheri1,**, Afshin Bakhtiari2 and Masoume Jaberi3 1 Young Researchers Club, Islamic Azad University, Science and Research Branch, Tehran 1477893855, Iran 2 Tehran Naftoon Arya Eng. Co., Jahanmehr St., Fatemi Sq., Tehran 1581768516, Iran 3 Department of Chemical Engineering, University of Tehran, Tehran 1136514563, Iran;Estimation of Formation Enthalpies of Organic Pollutants from a New Structural Group Contribution Method[J];Chinese Journal of Chemical Engineering;2013-06
7 LI Gao-yan,PAN Yong,JIANG Jun-cheng(Jiangsu Key Laboratory of Urban and Industrial Safety,College of Urban Construction and Safety Engineering,Nanjing University of Technology,Nanjing 210009,Jiangsu Province,China);Experimental study on flash points of binary organic mixtures[J];化学工程;2013-01
8 FANG Huijuan, LUO Jiliang and WANG Fei College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China;Fast Learning in Spiking Neural Networks by Learning Rate Adaptation[J];Chinese Journal of Chemical Engineering;2012-06
9 LI Fei,GE Liang-quan*,ZHANG Qing-xian,GU Yi,WAN Zhi-xiong,LI Wang-yan Chengdu University of Technology,Chengdu 610059,China;Research on the Application of Improved M-P Neural Network to the Determination of Lead and Zinc Ore Element Contents by Energy Disperse X-Ray Fluorescence Analysis[J];光谱学与光谱分析;2012-05
10 WANG Jianlin,FENG Xuying,ZHAO Liqiang and YU Tao College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China;Unscented Transformation Based Robust Kalman Filter and Its Applications in Fermentation Process[J];Chinese Journal of Chemical Engineering;2010-03
【Co-references】
Chinese Journal Full-text Database 3 Hits
1 FANG Huijuan, LUO Jiliang and WANG Fei College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China;Fast Learning in Spiking Neural Networks by Learning Rate Adaptation[J];Chinese Journal of Chemical Engineering;2012-06
2 LIN Xiang-hong1,2,ZHANG Tian-wen1(1.School of Computer Science and Technology,Harbin Institute of Technology,Harbin,Heilongjiang 150001,China;2.School of Mathematics and Information Science,Northwest Normal University,Lanzhou,Gansu 730070,China);Dynamical Properties of Piecewise Linear Spiking Neuron Model[J];电子学报;2009-06
3 FANG Hui-juan,WANG Yong-ji (Department of Control Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China);Spiking Neural Networks with Neurons Firing Multiple Spikes[J];应用科学学报;2008-06
【Secondary References】
Chinese Journal Full-text Database 1 Hits
1 XU Yan;College of Information Science and Technology,Nanjing Agricultural University;;Spiking Neuron Online Learning Method Based on Gradient Descent[J];计算机工程;2015-12
【Secondary Citations】
Chinese Journal Full-text Database 4 Hits
1 WANG Yong1),2) HU Bao-Gang1),2)1)(National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190)2)(Graduate University of Chinese Academy of Sciences,Beijing 100049);A Study on Integrated Evaluating Kernel Classification Performance Using Statistical Methods[J];计算机学报;2008-06
2 QIAN Yu LI Hehua LI XiuxiSchool of Chemical Engineering, South China University of Technology, Guangzhou 510640, China;A Multi-layer Information Integration Platform for Chemical Process Operation Systems[J];Chinese Journal of Chemical Engineering;2004-05
3 HUANG Dexian JIN Yihui ZHANG Jie A. J. MorrisDepartment of Automation, Tsinghua University, Beijing 100084, ChinaCPACT, Merz Court, University of Newcastle, Newcastle upon Tyne, NE1 7RU, U.K.;Non-linear Chemical Process Modelling and Application in Epichlorhydrine Production Plant Using Wavelet Networks[J];Chinese Journal of Chemical Engineering;2002-04
4 YANG Hui zhong *, ZHANG Su zhen (Research Institute of Automation ECUST, Shanghai 200237, China)$$$$;The Application of BFGS Revised Algorithm in Learning Feed Forward Neural Networks[J];华东理工大学学报;2001-05
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved