Luo Dehan, Chen Weihai. Active Back-propagation Algorithm Based on Adjusting Error for Multilayer Feed-forward Neural Network[J]. Journal of Beijing University of Aeronautics and Astronautics, 1998, 24(3): 350-353. (in Chinese)
Citation: Luo Dehan, Chen Weihai. Active Back-propagation Algorithm Based on Adjusting Error for Multilayer Feed-forward Neural Network[J]. Journal of Beijing University of Aeronautics and Astronautics, 1998, 24(3): 350-353. (in Chinese)

Active Back-propagation Algorithm Based on Adjusting Error for Multilayer Feed-forward Neural Network

  • Received Date: 25 Nov 1997
  • Publish Date: 31 Mar 1998
  • The back-propagation (BP) algorithm was used as a learning algorithm in training multilayer feed-forward neural networks (MLFNN) in past years, and some improved BP algorithms have recently been developed to speed up MLFNN learning. However, the effeciency of these improved BP algorithms are limited due to ignoring the activity of adjusting error during training MLFNN. In this paper, an active back propagation (ABP) algorithm based on improved BP algorithm is developed for MLFNN trained. The ABP algorithm alters the adjusting errors of MLFNN during the network trained, according to the error tendency of the network, and aimed to enhance rapidity of the network trained. The paper describes experiments that compare the performance of ABP algorithm with improved BP algorithms. The experiment results have shown that the ABP algorithm gives more efficient than improved BP algorithm for MLFNN trained.

     

  • 1 .Rumelhart De, McClelland Jl. Learning internal representation by error propagation.In:Rumelhart De,McClelland Jl,eds.Parallel Distributed Processing——Explorations in the Microstructure of Cognition. Vol. 1.Cambridge MA:MIT Press,1986.318~362 2. Baba N. A new approach for finding the global minimum of error function of neural networks.Neural Networks,1989,2(2):367~373 3. Hornik K, Stinhcombe M, White H.Multilayer feedforward networks are universal approximators. Neural Networks,1989,2(2):359~366 4. Minai Aa, Williams Rd.Acceleration of back propagation through learning rate and momentum adaptation.In:IEEE,eds.Proceedings of the International Joint Conference on Neural Networks.California:San Diego,1990.676~679 5. Lang Kj, Witbrock Mj. Faster learning variations on back-propagation: an empirical study.In:Toure tzky Ds,Hinton Ge,Sejnowski Tj,eds.Proc Connectionist Models Summer School. San Mateo:Morgan Kaufmann, 1988.52~59 6. Riedmiller M, Braun H. A direct adaptative method for faster backpropagation learning: the RPROP Algorithm.In:IEEE,eds.Proceedings of International Neural Networks. San francisco, 1993.586~591 7. Shiffman W, Joost M, Werner R. Optimization of the back propagation algorithm for training multilayer perceptrons.Proc European Symposium on Artificial Neural Networks, ESANN 93. Brussels,1993.97~104
  • Relative Articles

    [1]ZHANG F X,GAO T,WU H D. Improved chimpanzee search algorithm based on multi-strategy fusion and its application[J]. Journal of Beijing University of Aeronautics and Astronautics,2025,51(1):235-247 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0891.
    [2]XING Z W,SUN K,LUO Q,et al. Imputation algorithm for flight ground support data based on graph neural network[J]. Journal of Beijing University of Aeronautics and Astronautics,2025,51(5):1528-1538 (in Chinese). doi: 10.13700/j.bh.1001-5965.2023.0300.
    [3]BAI He, LI Yu, HAO Ming, XU Tingting. Graph neural network recommendation algorithm fused with dual-channel attention and time encoding[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0795
    [4]YANG Liangliang, WO Yang, LU Wenqi. Improved algorithm for motor feedforward parameter tuning based on instrumental variable method[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2025.0023
    [5]WANG Y Z,Li X,MOU R,et al. Improved SEGAN based ATC speech enhancement algorithm for air traffic control[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(12):3930-3939 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0874.
    [6]HE J W,XU X Z,GAO B. Improved moth-flame optimization algorithm with multi-strategy integration[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(9):2862-2871 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0707.
    [7]JIANG Y F,XU X Z,XU F Q,et al. Multi-strategy fusion improved adaptive mayfly algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(4):1416-1426 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0492.
    [8]YU Ming-yang, LI Ting, XU Jing. Enhanced Dwarf Mongoose Optimization Algorithm with Multi-Strategy fusion[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023-0613
    [9]SHI T X,CHEN L S,LI T S,et al. Distributed adaptive anti-disturbance control for power systems based on multi-agents[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(5):1685-1692 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0496.
    [10]YANG X X,JIANG Z J,ZHANG Y,et al. Distributed cooperative guidance strategy based on virtual negotiation and rolling horizon optimization[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(1):61-76 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0174.
    [11]NA Qiang, XIANG Peng, ZHENG Huaizhou, ZHOU Shun, HE Hongye. Similarity Analysis of Pre-Launch Data for Aerospace Rocket Testing Based on Adaptive DTW Algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0524
    [12]ZHOU Y J,WAN Q,XU Y Z,et al. Redundancy design of a FADS system on a complex leading-edge vehicle using neural network approach[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(3):757-764 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0341.
    [13]CAO Hao, CHEN Yiou, ZHANG Runze. A BP decoding algorithm for polar codes based on task graph reconstruction[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0407
    [14]ZHAO S,LIN L,LI Z,et al. Deck motion prediction and compensation technology based on BP neural network[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(9):2772-2780 (in Chinese). doi: 10.13700/j.bh.1001-5965.2022.0743.
    [15]LI L,FU M H,ZHANG T,et al. A workpiece location algorithm based on improved SSD[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(6):1260-1269 (in Chinese). doi: 10.13700/j.bh.1001-5965.2021.0442.
    [16]JIANG L,SUN R,LIU Z W,et al. Modeling and accuracy analysis of GNSS ionospheric error in EU-China based on GA-BP[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(6):1533-1542 (in Chinese). doi: 10.13700/j.bh.1001-5965.2021.0476.
    [17]LONG Yuan, DENG Xiaolong, YANG Xixiang, HOU Zhongxi. Short-term rapid prediction of stratospheric wind field based on PSO-BP neural network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(10): 1970-1978. doi: 10.13700/j.bh.1001-5965.2021.0068
    [18]Wen Jingqian, Li Qing, Zhao Qingbin. Method to analyze the impact of maintenance and support process based on neural network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2011, 37(6): 690-694.
    [19]Wang Zijian, Zhang Jun, Luo Xiling. Distributed power aware topology control algorithm for self-organizing networks[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(01): 55-58.
    [20]Fang Jiancheng, Li Jianli, Sheng Wei. Improved temperature error model of silicon MEMS gyroscope with inside frame driving[J]. Journal of Beijing University of Aeronautics and Astronautics, 2006, 32(11): 1277-1280.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views(3035) PDF downloads(872) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return