Optimal Sizing of Feedforward Neural Networks: Case Studies

Authors:
K. W. Lee;H. N. Lam
Affiliations:
-;-
Venue:
ANNES '95 Proceedings of the 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems
Year:
1995

Citing 0
Cited 4

Specification of Training Sets and the Number of Hidden Neurons for Multilayer Perceptrons

Neural Computation
Multi step ahead prediction of north and south hemisphere sun spots chaotic time series using focused time lagged recurrent neural network model

WSEAS Transactions on Information Science and Applications
Novel FTLRNN with gamma memory for short-term and long-term predictions of chaotic time series

Applied Computational Intelligence and Soft Computing
Modeling plasma surface modification of textile fabrics using artificial neural networks

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Feedforward neural networks with sigmoidal hidden layers can be used to approximate any continuous functions within allowable tolerances in accuracy. However, no systematic rules are available for the determination of the optimal number of hidden nodes for the networks. In this paper, an algorithm is proposed which can be employed to find the optimal number of hidden nodes in FNNs used for function approximation. The algorithm has advantages over the conventional trial and error method as the computational time will be reduced and there will be a lower probability of solutions getting stuck at local minima. Two case studies are made to investigate the performance of the algorithm yielding encouraging results.