Title :
Geometrical interpretation and architecture selection of MLP
Author :
Xiang, Cheng ; Ding, Shenqiang Q. ; Lee, Tong Heng
Author_Institution :
Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore
Abstract :
A geometrical interpretation of the multilayer perceptron (MLP) is suggested in this paper. Some general guidelines for selecting the architecture of the MLP, i.e., the number of the hidden neurons and the hidden layers, are proposed based upon this interpretation and the controversial issue of whether four-layered MLP is superior to the three-layered MLP is also carefully examined.
Keywords :
multilayer perceptrons; neural net architecture; MLP architecture selection; MLP geometrical interpretation; multilayer perceptron; Art; Artificial neural networks; Computer architecture; Function approximation; Guidelines; Multilayer perceptrons; Neural networks; Neurons; Nonhomogeneous media; Shape; Architecture selection; geometrical interpretation; multilayer perceptron (MLP); Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Computing Methodologies; Models, Statistical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2004.836197
