期刊文献+

一种基于二阶导数的 BP 算法 被引量:2

A New BP Algorithm Based on Second Derivative
下载PDF
导出
摘要 根据神经网络模型的结构特点,将能量函数的二阶导数与最速下降方向相结合,构造出一种新型的BP算法,该算法比梯度法收敛快,较牛顿法计算量小.它适合于计算结构复杂的BP神经网络模型,理论分析表明该算法行之有效,计算机仿真达到了理想的效果. Based on the architectural features of the neural network, a new BP algorithm is developed by combining the gradient direction with the second derivative of the energy function. It is shown that the rate of convergence of the algorithm proposed is faster the that of gradient method, and its amount of work is less than that of Newton method. It is fairly suitable to the calculation of a BP neural network model of complicated architecture.
出处 《华中理工大学学报》 CSCD 北大核心 1998年第3期105-107,共3页 Journal of Huazhong University of Science and Technology
基金 国家自然科学基金
关键词 BP算法 神经网络 能量函数 梯度法 二阶导数 descent direction BP algorithm neural network energy function gradient method Newton method
  • 引文网络
  • 相关文献

参考文献4

  • 1徐秉铮,神经网络理论与应用,1994年
  • 2俞玉森,数学规划的原理和方法,1993年
  • 3魏权龄,数学规划引论,1991年
  • 4陈保林,最优化理论与算法,1989年

同被引文献11

  • 1金伟其,胡威捷.辐射度,光度与色度及其测量[M].北京理工大学出版社,2006,10.
  • 2CIE 191: 2010 Recommended System for Mesopic Photometry Based on Visual Performance [ M ]. 4 - 5, 14 -16, 19-21, 24-30.
  • 3Goodman T, Forbes A, Walker H, et al. Mesopic visual efficiency IV: a model with relevance to nighttime driving and other applications Light Res. Technol. 2007 39 (11) : 365 -392.
  • 4Chen Shouyu. Relative membership function and frame of fuzzy sets theory for pattern recognition [J].Journal of Fuzzy Mathematics, 1997, 5 (2): 401-411.
  • 5Chen Shouyu. Fuzzy recognition theoretic model [J]. Journal of Fuzzy Mathematics, 1993, (2): 261 -269.
  • 6Chen Shouyu, Nie Xiangtian. Forecasting model of neural network with fuzzy pattern recognition and evolution simplex method [J]. Journal of Fuzzy Mathematics, 1999, (4): 913- 923.
  • 7林成森.数值计算方法[M].北京:科学出版社,1998..
  • 8陈守煜.模糊优选神经网络多目标决策理论[J].大连理工大学学报,1997,37(6):693-698. 被引量:20
  • 9潘建根,李艳.CIE中间视觉光度学推荐系统[J].中国照明电器,2010(12):9-9. 被引量:5
  • 10陈守煜,赵瑛琪.模糊优选理论与模型[J].模糊系统与数学,1990,4(2):87-91. 被引量:60

引证文献2

二级引证文献11

;
使用帮助 返回顶部