Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/1817
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Guan, SU | - |
dc.contributor.author | Liu, J | - |
dc.coverage.spatial | 37 | en |
dc.date.accessioned | 2008-03-10T13:05:14Z | - |
dc.date.available | 2008-03-10T13:05:14Z | - |
dc.date.issued | 2002 | - |
dc.identifier.citation | Journal of Intelligent Systems. 12 (3) 137-172 | en |
dc.identifier.issn | 0334-1860 | - |
dc.identifier.uri | http://bura.brunel.ac.uk/handle/2438/1817 | - |
dc.description.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. | en |
dc.format.extent | 133789 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | Freund & Pettman | en |
dc.relation.ispartof | 12;3 | - |
dc.subject | Ordered training | en |
dc.subject | Incremental training | en |
dc.subject | Neural networks | en |
dc.subject | Input attributes | en |
dc.title | Incremental ordered neural network training | en |
dc.type | Research Paper | en |
Appears in Collections: | Electronic and Electrical Engineering Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Incremental Ordered Neural Network Training.txt | 262 B | Text | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.