Please use this identifier to cite or link to this item: https://doi.org/10.1162/089976601317098565
Title: Feedforward neural network construction using cross validation
Authors: Setiono, R. 
Issue Date: 2001
Source: Setiono, R. (2001). Feedforward neural network construction using cross validation. Neural Computation 13 (12) : 2865-2877. ScholarBank@NUS Repository. https://doi.org/10.1162/089976601317098565
Abstract: This article presents an algorithm that constructs feedforward neural networks with a single hidden layer for pattern classification. The algorithm starts with a small number of hidden units in the network and adds more hidden units as needed to improve the network's predictive accuracy. To determine when to stop adding new hidden units, the algorithm makes use of a subset of the available training samples for cross validation. New hidden units are added to the network only if they improve the classification accuracy of the network on the training samples and on the cross-validation samples. Extensive experimental results show that the algorithm is effective in obtaining networks with predictive accuracy rates that are better than those obtained by state-of-the-art decision tree methods.
Source Title: Neural Computation
URI: http://scholarbank.nus.edu.sg/handle/10635/42526
ISSN: 08997667
DOI: 10.1162/089976601317098565
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

65
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

51
checked on Nov 16, 2017

Page view(s)

590
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


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