DocumentCode
2186338
Title
Perceptron Multilayer Artificial Neural Network with Good Generalization
Author
Yubo, Tian ; Yue, Dong ; Xiaoqiu, Zhang ; Renjie, Zhu
Author_Institution
Jiangsu Univ. of Sci. & Technol., Zhenjiang
fYear
2007
fDate
17-21 Sept. 2007
Firstpage
826
Lastpage
829
Abstract
Feedforward perceptron multilayer (PML) ANNs with error back propagation learning method is often used in engineering design. Unfortunately, its generalization is often poor. In this paper, some reformative methods are proposed to improve its generalization. Based on the improved PML ANN, E-plane T-kind terminal matched load of rectangular waveguide is designed successfully. The result given by the ANN is agreeable with FDTD very well.
Keywords
backpropagation; finite difference time-domain analysis; multilayer perceptrons; FDTD; error back propagation learning method; perceptron multilayer artificial neural network; rectangular waveguide; Artificial neural networks; Convergence; Finite difference methods; Learning systems; Least squares approximation; Microwave technology; Multi-layer neural network; Multilayer perceptrons; Neurons; Time domain analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Electromagnetics in Advanced Applications, 2007. ICEAA 2007. International Conference on
Conference_Location
Torino
Print_ISBN
978-1-4244-0767-5
Electronic_ISBN
978-1-4244-0767-5
Type
conf
DOI
10.1109/ICEAA.2007.4387431
Filename
4387431
Link To Document