Number determination of hidden-layer nodes for Hermite feed-forward neural network

被引：2
|
作者：
Zhang Y.-N. [1 ]
Xiao X.-C. [1 ]
Chen Y.-W. [2 ]
Zou A.-J. [1 ]
机构：
[1] Department of Electronics and Communication Engineering, Sun Yat-Sen University
[2] School of Software, Sun Yat-Sen University
来源：
Zhejiang Daxue Xuebao(Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2010年 / 44卷 / 02期
关键词：
Hermite neural network; Number of hidden-layer nodes; Pseudo-inverse; Weights-direct-determination;
D O I：
10.3785/j.issn.1008-973X.2010.02.011
中图分类号：
学科分类号：
摘要：
A new feed-forward neural network was constructed by using Hermite orthogonal polynomial as activation function, which originated from the function-approximation theory. All neural bias and weights from input to hidden layer were respectively fixed to be 0 and 1 with approximation capability guaranteed, and a pseudo-inverse based direct-determination method was derived for the optimal neural weights from hidden layer to output layer. Then an order-increasing automatic-determination algorithm was presented for the optimal number of hidden-layer neurons according to the precision requirement. Computer simulation and prediction results based on multiple target-functions show that the proposed algorithms can quickly obtain the optimal number and weights of hidden-layer neurons and have a relatively good prediction capability.
引用
收藏
页码：271 / 275
页数：4
相关论文
共 14 条
  • [1] Zhang Y.-N., Wang J., Recurrent neural networks for nonlinear output regulation, Automatica, 37, 8, pp. 1161-1173, (2001)
  • [2] Zhang Y.-N., Wang J., Obstacle avoidance of kinematically redundant manipulators using a dual neural network, IEEE Transactions on Systems, Man, and Cybernetics, 34, 1, pp. 752-759, (2004)
  • [3] Zhang Y.-N., Ge S.-Z., Lee T.-H., A unified quadratic programming based dynamical system approach to joint torque optimization of physically constrained redundant manipulators, IEEE Transactions on Systems, Man and Cybernetics, 34, 5, pp. 2126-2132, (2004)
  • [4] Zhang Y.-N., Jiang D.-C., Wang J., A recurrent neural network for solving sylvester equation with time-varying coefficients, IEEE Transactions on Neural Networks, 13, 5, pp. 1053-1063, (2002)
  • [5] Zhang Y.-N., Ge S.-Z., Design and analysis of a general recurrent neural network model for time-varying matrix inversion, IEEE Transactions on Neural Networks, 16, 6, pp. 1477-1490, (2005)
  • [6] Zhang Q.-L., Wang S.-Q., Nonlinear predictive functional control based on a neural network, Journal of Zhejiang University: Engineering Science, 35, 5, pp. 497-501, (2001)
  • [7] (2007)
  • [8] pp. 113-116, (2003)
  • [9] Lu X.-Q., Yu Y.-L., A method of dynamic pruning the hidden layer nodes in a feedforward neural network, Control Theory and Application, 14, 1, pp. 101-104, (1997)
  • [10] Zhao Q.-L., Chen B., Zhuo J.-S., Self-dele-ting algorithm of feedforward neural networks, Journal of HoHai University, 28, 4, pp. 63-66, (2000)
12