Weights and Structure Determination of Feed-Forward Two-Input Neural Network Activated by Chebyshev Polynomials of Class 2
Based on the theory of polynomial interpolation and approximation, a new feed-forward two-input neural network activated by a group of Chebyshev polynomials of Class 2 (i.e., TINN-CP2) is constructed and investigated in this paper. To overcome the weaknesses of conventional back-propagation (BP) neural networks, a weights-direct-determination (WDD) method is exploited to obtain the optimal linking weights of the proposed neural network directly. Furthermore, a new structure-automatic-determination (SAD) algorithm is developed to determine the optimal number of hidden-layer neurons of the TINN-CP2, and thus the weights-and-structuredetermination (WASD) algorithm is built up. Numerical studies further substantiate the ef.cacy and superior abilities of the proposed TINN-CP2 in approximation, denoising and prediction, with the aid of the WASD algorithm which obtains the optimal number of hidden-layer neurons of the TINN-CP2.
Chebyshev polynomials of Class 2 Feedforward two-input neural network Weights-and-structuredetermination (WASD) algorithm Optimal linking weights BP neural networks
Yunong Zhang Xiaotian Yu Dongsheng Guo Jun Li Zhengping Fan
School of Informantion Science andTechnology, Sun Yat-sen University, Guangzhou 510006, P. R. China School of Informantion Science and Technology, Sun Yat-sen University, Guangzhou 510006, P. R. China
国际会议
The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)
太原
英文
1100-1105
2012-05-23（万方平台首次上网日期，不代表论文的发表时间）