Optimizing the number of hidden layer neurons for an FNN (feedforward neural network) to solve a practical problem remains one of the unsolved tasks in this research area. In this paper we review several mechanisms in the neural networks literature which have been used for determining an optimal number of hidden layer neuron (given an application), propose our new approach based on some mathematical evidence, and apply it in financial data mining. Compared with the existing methods, our new approach is proven (with mathematical justification), and can be easily handled by users from all application fields.

Item Type:	Refereed Conference Paper
Keywords:	neural networks, data mining, number of hidden layer neurons
Research Division:	Information and Computing Sciences
Research Group:	Artificial Intelligence and Image Processing
Research Field:	Neural, Evolutionary and Fuzzy Computation
Objective Division:	Information and Communication Services
Objective Group:	Computer Software and Services
Objective Field:	Computer Software and Services not elsewhere classified
UTAS Author:	Xu, S (Dr Shuxiang Xu)
ID Code:	54013
Year Published:	2008
Deposited By:	Information and Communication Technology
Deposited On:	2009-02-06
Last Modified:	2014-10-20
Downloads:	91 View Download Statistics