Geometrical interpretation and architecture selection of MLP

Authors:
Cheng Xiang;S. Q. Ding;Tong Heng Lee
Affiliations:
Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
2005

Citing 0
Cited 5

Overfitting problem: a new perspective from the geometrical interpretation of MLP

Design and application of hybrid intelligent systems
QoS-aware roadside base station assisted routing in vehicular networks

Engineering Applications of Artificial Intelligence
An efficient method for pruning the multilayer perceptron based on the correlation of errors

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Estimating the number of hidden neurons in a feedforward network using the singular value decomposition

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Numerical assessment of metamodelling strategies in computationally intensive optimization

Environmental Modelling & Software

Quantified Score

Hi-index	0.00

Visualization

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.