Please use this identifier to cite or link to this item:
|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.
checked on Jul 31, 2021
WEB OF SCIENCETM
checked on Jul 22, 2021
checked on Aug 1, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.