Please use this identifier to cite or link to this item:
Title: On R2 contribution and statistical inference of the change in the hidden and input units of the statistical neural networks
Authors: Udomboso, C. G.
James, T. O.
Odim, M. O.
Keywords: Hidden Unit
Input Unit
R2 change
F test
Issue Date: Nov-2012
Publisher: Society of African Journal Editors
Abstract: Determining the number of liitltlen units for obtaining optimal network performance has been a concern over the years ilespite empirical results showing that with higher neurons, the netivork error is retlucetl. This has led to indiscrimate increase in the hidden neurons, thereby bringing about overfitting. On the other hand, using too few hidden neurons leads to error bias, which can make neural network statistically unfit. In this paper, we developed a model for R1 for investigating changes in hidden and input units, as well as developed tests that can be used in determining the number of hidden and input units to obtain optimal performance. The result of the analyses shows that there is effect on the network model when there is an increase in the number of hidden neurons, as well as the number of input units.
ISSN: 1116-4336
Appears in Collections:Scholarly works

Files in This Item:
File Description SizeFormat 
(16) ui_art_udomboso_on_2012.pdf2.7 MBAdobe PDFThumbnail

Items in UISpace are protected by copyright, with all rights reserved, unless otherwise indicated.