Please use this identifier to cite or link to this item: https://doi.org/10.1109/72.363426
Title: Use of a quasi-Newton method in a feedforward neural network construction algorithm
Authors: Setiono, Rudy 
Hui, Lucas Chi Kwong 
Issue Date: Jan-1995
Citation: Setiono, Rudy, Hui, Lucas Chi Kwong (1995-01). Use of a quasi-Newton method in a feedforward neural network construction algorithm. IEEE Transactions on Neural Networks 6 (1) : 273-277. ScholarBank@NUS Repository. https://doi.org/10.1109/72.363426
Abstract: Interest in algorithms which dynamically construct neural networks has been growing in recent years. This paper describes an algorithm for constructing a single hidden layer feedforward neural network. A distinguishing feature of this algorithm is that it uses the quasi-Newton method to minimize the sequence of error functions associated with the growing network. Experimental results-indicate that the algorithm is very efficient and robust. The algorithm was tested on two test problems. The first was the n-bit parity problem and the second was the breast cancer diagnosis problem from the University of Wisconsin Hospitals. For the n-bit parity problem, the algorithm was able to construct neural network having less than n hidden units that solved the problem for n = 4, ···, 7. For the cancer diagnosis problem, the neural networks constructed by the algorithm had small number of hidden units and high accuracy rates on both the training data and the testing data.
Source Title: IEEE Transactions on Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/99454
ISSN: 10459227
DOI: 10.1109/72.363426
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

129
checked on Aug 14, 2018

WEB OF SCIENCETM
Citations

100
checked on Jul 25, 2018

Page view(s)

31
checked on Aug 17, 2018

Google ScholarTM

Check

Altmetric


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