期刊文献+

无学习率权值调整神经计算法拟合范德堡多项式 被引量:1

Neurocomputing Van der Pauw Function without Learning Rate of Weight Vector Regulation
下载PDF
导出
摘要 提出了一种新的神经计算的方法,其最大的特点是在进行特定的权值调整时无须加入学习率。计算开始时先给出一组随机的权值作为被拟合多项式的系数,由这组权值得到的拟合点上被拟合多项式值与期望值的各误差绝对值之和。依据其小分数的负值直接来调整权值,使各误差之绝对值不断减小,通过反复迭代计算,最终当各误差都在规定范围内时便得到期望的权值。在实际的计算中利用这种方法进行曲线拟合能方便地求出拟合多项式的系数,便于编程,简化了计算过程。将这种方法应用到范德堡函数的多项式拟合中,得到了范德堡函数f=1+0.03237714η-0.04037678η2+0.00857881η3-0.00077693η4+0.00002604η5并画出了曲线。 A new neurocomputing method is presented. Its major characteristic is not need to use the learning rate, when it carries on the weight adjustment in the iteration process. In the beginning of computing, an arbitrary set of weights as coefficients of polynomial were first imputed. The absolute summation of the errors between the computed polynomial and the expectations on the matched points were obtained. A small and negative fraction of it was taken as the weight adjustment , so as to minimize each absolute error. After a lot of iteration computations, each error was converged to a specified very litter one, then the expected weights were finally obtained. Using this method, the optimum weights can be able to be extracted conveniently. As like this simplified computation process, the advantages is easy to compile the computer programming. We apply this method to the polynomial fitting for Van der Pauw function,a quite satisfactory result is finally obtained, plotting a corresponding curve.
出处 《电子器件》 CAS 2008年第3期1015-1018,共4页 Chinese Journal of Electron Devices
关键词 神经网络 学习率 多项式拟合 范德堡函数 neural network learning rate polynomial fitting Van der Pauws function
  • 相关文献

参考文献9

  • 1Van der Pauw L.T.Philip Research Reports,1958,13:1.
  • 2Rymaszewski R.Electron Lett[J].1967,3:57.
  • 3Sun Yieai,Shi Jtmsheng,Meng Qinghao.Measurement of Sheet Resistance of Cross Microareas using a Modified Van der Pauw Method[J].Semicond Sei Teehnol,1996,11:805-811.
  • 4Shi Junsheng,Sun Yieai,New Method of Calculating the Cor-rection Factor for the Measurement of Sheet Resistance of a Square Sample with a Square four Point Probe[J].Rev Sci In-strum 1997,68 (4):1814-1817.
  • 5张艳辉,孙以材,刘新福,陈志永.斜置式方形探针测量单晶断面电阻率分布mapping技术[J].Journal of Semiconductors,2004,25(6):682-686. 被引量:7
  • 6ASTM[M].F76-68,1971 Annual book,part 8,1971:652.
  • 7Robert H N,Neurocomputing[M].Addison-Wesley Publish-ing Company (1990),New York 47-89.
  • 8Mirszal A R.Artificial Intelligence[M].Chapman and Hall,(1990),London 97-103.
  • 9王静,孙以材,刘新福.利用多项式拟合规范化方法实现范德堡函数的高精度反演[J].Journal of Semiconductors,2003,24(8):817-821. 被引量:16

二级参考文献10

共引文献16

同被引文献8

  • 1Sun Yicai, Meng Qinghao, Chen Zhiyong, et al. Normalizingthepolynomial-matchforthenon-linearsignalintransducers [J]. Sensors and Actuators A, 2005 (125): 76-83.
  • 2Martin T Hagan, Howard B Demuth, Mark H Beale. Neural network design [M]. PWS Publishing Company, 1996.
  • 3Robert H N. Neurocomputing [M]. New York: Addison-Wesley Publishing Company, 1990.
  • 4Mirszal A R. Artificial Intelligence [M]. London: Chapman and Hall, 1990.
  • 5Sun Yicai, Shi Junsheng, Meng Qinghao. Measurement of sheet resistance of cross microareas using a modified Van der Pauw method [J]. Semieond Sci Technol, 1996 (11): 805-811.
  • 6ASTM F76-68, 1971 AnnualBook, part 8 [Z]. 1971, 652-668.
  • 7张耀锋,孙以材,邢晓辉.基于人工神经网络的压力传感器的温度补偿[J].电子学报,2008,36(2):358-361. 被引量:35
  • 8王静,孙以材,刘新福.利用多项式拟合规范化方法实现范德堡函数的高精度反演[J].Journal of Semiconductors,2003,24(8):817-821. 被引量:16

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部