Brunel University Research Archive (BURA) >
Schools >
School of Engineering and Design >
School of Engineering and Design Research papers >

Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/1817

Title: Incremental ordered neural network training
Authors: Guan, SU
Liu, J
Keywords: Ordered training
Incremental training
Neural networks
Input attributes
Publication Date: 2002
Publisher: Freund & Pettman
Citation: Journal of Intelligent Systems. 12 (3) 137-172
Abstract: This paper investigates the incremental training of a Neural Network (NN) with the input attributes introduced in order. A specially designed NN is used to evaluate the individual discrimination ability of each input attribute. Attributes are then sorted in descending, ascending, and random orders of their individual discrimination abilities and introduced into another NN being trained with an incremental training algorithm, ITID. To reduce the inter-ference caused by irrelevant features and high-complexity tasks, only relevant features are involved and tasks are decomposed in the experiments. The experimental results of several benchmark problems show that descending order obtains the highest generalization accuracy among the three training orders for both classification and regression problems.
URI: http://bura.brunel.ac.uk/handle/2438/1817
ISSN: 0334-1860
Appears in Collections:School of Engineering and Design Research papers
Electronic and Computer Engineering

Files in This Item:

File Description SizeFormat
Incremental Ordered Neural Network Training.txt262 BTextView/Open

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