An Accurate and Robust Online Sequential Learning Algorithm for Feedforward Networks

Abstract

Abstract:

Abstract： In this paper, a kind of accurate and robust online sequential learning algorithm was proposed for single hidden layer feedforward networks. The algorithm is referred to as online sequential discrete Fourier transformextreme learning machine (OSDFTELM). This approach is able to learn data onebyone or chunkbychunk. During the growth of the data, input weights and output weights are adjusted incrementally. The proposed algorithm has a higher degree of accuracy and robustness compared to the approach referred to as online sequentialextreme learning machine (OSELM). Two simulation examples were presented to show the excellent performance of the proposed approach.

Key words: single hidden layer feedforward networks, online sequential learning machine, extreme learning machine

CLC Number:

LU Chengbo，MEI Ying. An Accurate and Robust Online Sequential Learning Algorithm for Feedforward Networks[J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1137-1143.

References

［1］Man Z H, Lee K, Wang D H, et al. Robust singlehidden layer feedforward networkbased pattern classifier ［J］. IEEE Transactions on Neural Networks and Learning Systems，2012，23(12)：19741986.

［2］Liang N Y, Huang G B, Saratchandran P, et al. A fast and accurate online sequential learning algorithm for feedforward networks ［J］. IEEE Transactions on Neural Networks，2006，17(6)：14111423.

［3］Haykin S. Neural networks and learning machines ［M］. 3rd ed. New Jersey：Pearson, PrenticeHall，2009.

［4］Kumar S. Neural networks ［M］. New York：McGrawHill Companies, Inc，2006.

［5］Yao X. Evolving artificial neural networks ［J］. Proceedings of the IEEE，1999，87(9)：14231447.

［6］Zhang G, Neural networks for classification: a survey ［J］. IEEE Transactions on Systems, Man and Cybernetics：Part C，2000(30)：451462.

［7］Hertz J, Krogh A, Palmer R G. Introduction to the theory of neural computations ［M］. Boston: AddisonWesley Publishing Company，1991.

［8］Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes ［J］. IEEE Transactions on Neural Networks，2006，17(4)：879892.

［9］Igelnik B, Pao Y H. Stochastic choice of basis functions in adaptive function approximation and the functionallink net ［J］. IEEE Transactions on Neural Networks，1995，6 (6)：13201329.

［10］乔俊飞，韩红桂. 前馈神经网络分析与设计［M］.北京：科学出版社，2013.

［11］Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation ［J］. Parallel Distribution Processing: Explanations in the Microstructure of Cognition, 1986(1)：318362.

［12］Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications ［J］. Neurocomputing, 2006，70(13)：489501.

［13］Huang G B, Wang D H, Lan Y. Extreme learning machines：A survey ［J］. International Journal of Machine Learning and cybernetics, 2011，2(2)： 107122.

［14］Golub G H, Loan C F. Matrix computations ［M］. 3rd ed. Baltimore：The Johns Hopkins University Press，1996.

［15］Lecun Y, Bottou L, Bengio Y, et al. Gradientbased learning applied to document recognition ［J］. Proceedings of the IEEE,1998，86(11)：22782324.

[1]	JIN Haochun, GE Minhui, XU Bo. Optimization of DFIG Comprehensive Adaptive Frequency Regulation Parameters Based on Extreme Learning Machine [J]. Journal of Shanghai Jiao Tong University, 2021, 55(S2): 42-50.
[2]	XI Jianhui, JIANG Han, CHEN Bo, FU Li. Infrared Multispectral Radiation Temperature Measurement Based on PCA-ELM [J]. Journal of Shanghai Jiao Tong University, 2021, 55(7): 891-898.
[3]	LI Chunxiang, ZHANG Haoyi. Hybridizing Multivariate Empirical Mode Decomposition and Extreme Learning Machine to Predict Non-Stationary Processes [J]. Journal of Shanghai Jiao Tong University, 2020, 54(4): 376-386.
[4]	ZHANG Linlin,HU Xiongwei,LI Peng,SHI Fang,YU Zhihong. Power System Transient Stability Assessment Based on Extreme Learning Machine [J]. Journal of Shanghai Jiaotong University, 2019, 53(6): 749-756.
[5]	LIU Min,ZHANG Yingtang,LI Zhining,FAN Hongbo. Diesel Engine Fault Online Diagnosis Method Based on Incremental Sparse Kernel Extreme Learning Machine [J]. Journal of Shanghai Jiaotong University, 2019, 53(2): 217-224.
[6]	ZHONG Guoqiang,WANG Hao,ZHANG Guohua,QIN Weimin WANG Chengtang,XIONG Junfeng. Analysis and Prediction of Factors Affecting Horizontal Displacement of Foundation Pit Based on RS-MIV-ELM Model [J]. Journal of Shanghai Jiaotong University, 2018, 52(11): 1508-1515.
[7]	WU Bin1* (吴斌), XI Lifeng2 (奚立峰), FAN Sixia1 (范思遐), ZHAN Jian1 (占健). Fault Diagnosis for Wind Turbine Based on Improved Extreme Learning Machine [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(4): 466-473.
[8]	ZHANG Wei，XU Aiqiang，GAO Mingzhe. An Online Condition Prediction Algorithm Based on Cumulative Coherence Measurement [J]. Journal of Shanghai Jiaotong University, 2017, 51(11): 1391-1398.
[9]	WANG Ping,WANG Di,FENG Wei. Online Semi-Supervised Extreme Learning Machine Based on Manifold Regularization [J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1153-1158.
[10]	LIU Feifei,PENG Di,HE Yanlin,ZHU Qunxiong. Research and Chemical Application of Extreme Learning Based Process Neural Network [J]. Journal of Shanghai Jiaotong University, 2014, 48(07): 977-981.
[11]	ZHANG Yingtang,MA Chao,LI Zhining,FAN Hongbo. Online Modeling of Kernel Extreme Learning Machine Based on Fast Leave-One-Out CrossValidation [J]. Journal of Shanghai Jiaotong University, 2014, 48(05): 647-652.
[12]	PAN Feng1* (潘峰), ZHAO Hai-bo2 (赵海波). Online Sequential Extreme Learning Machine Based Multilayer Perception with Output Self Feedback for Time Series Prediction [J]. Journal of shanghai Jiaotong University (Science), 2013, 18(3): 366-375.
[13]	LIU Xue-Yi-a, LI Ping-a, b , GAO Chuan-Hou-c. Fast Leave-One-Out Cross-Validation Algorithm for Extreme Learning Machine [J]. Journal of Shanghai Jiaotong University, 2011, 45(08): 1140-1145.
[14]	ZHANG Xian,WANG Hongli . Local Extreme Learning Machine and Its Application to Condition Online Monitoring [J]. Journal of Shanghai Jiaotong University, 2011, 45(02): 236-0240.