Please use this identifier to cite or link to this item:
|Title:||Feedforward neural network construction using cross validation||Authors:||Setiono, R.||Issue Date:||2001||Citation:||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.
checked on May 16, 2019
WEB OF SCIENCETM
checked on May 8, 2019
checked on May 13, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.