Please use this identifier to cite or link to this item:
|Title:||Improving backpropagation learning with feature selection||Authors:||Setiono, R.
Feedforward neural network
|Issue Date:||1996||Citation:||Setiono, R.,Liu, H. (1996). Improving backpropagation learning with feature selection. Applied Intelligence 6 (2) : 129-139. ScholarBank@NUS Repository.||Abstract:||There exist redundant, irrelevant and noisy data. Using proper data to train a network can speed up training, simplify the learned structure, and improve its performance. A two-phase training algorithm is proposed. In the first phase, the number of input units of the network is determined by using an information base method. Only those attributes that meet certain criteria for inclusion will be considered as the input to the network. In the second phase, the number of hidden units of the network is selected automatically based on the performance of the network on the training data. One hidden unit is added at a time only if it is necessary. The experimental results show that this new algorithm can achieve a faster learning time, a simpler network and an improved performance. © 1996 Kluwer Academic Publishers.||Source Title:||Applied Intelligence||URI:||http://scholarbank.nus.edu.sg/handle/10635/99308||ISSN:||0924669X|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Mar 28, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.