Vasconcelos, G.C., Fairhurst, Michael, Bisset, D.L. (1995) INVESTIGATING FEEDFORWARD NEURAL NETWORKS WITH RESPECT TO THE REJECTION OF SPURIOUS PATTERNS. Pattern Recognition Letters, 16 (2). pp. 207-212. ISSN 0167-8655. (doi:10.1016/0167-8655(94)00092-h) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:19104)
| The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. | |
| Official URL: https://doi.org/10.1016/0167-8655(94)00092-h |
Abstract
The reliability of feedforward neural networks with respect to the rejection of patterns not belonging to the defined training classes is investigated. It is shown how networks with different activation functions and propagation rules construct the decision regions in the pattern space and, therefore, affect the network's performance in dealing with spurious information. A modification to the standard MLP structure is described to enhance its reliability in this respect.
| Item Type: | Article |
|---|---|
| DOI/Identification number: | 10.1016/0167-8655(94)00092-h |
| Uncontrolled keywords: | FEEDFORWARD NEURAL NETWORKS; PATTERN CLASSIFICATION |
| Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science |
| Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts |
| Depositing User: | I.T. Ekpo |
| Date Deposited: | 22 May 2009 14:58 UTC |
| Last Modified: | 05 Nov 2024 09:55 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/19104 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):
Altmetric
Altmetric
