INVESTIGATING FEEDFORWARD NEURAL NETWORKS WITH RESPECT TO THE REJECTION OF SPURIOUS PATTERNS

Vasconcelos, G.C. and Fairhurst, Michael and 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. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)

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
Uncontrolled keywords: FEEDFORWARD NEURAL NETWORKS; PATTERN CLASSIFICATION
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts
Depositing User: I.T. Ekpo
Date Deposited: 22 May 2009 14:58
Last Modified: 19 May 2014 11:01
Resource URI: http://kar.kent.ac.uk/id/eprint/19104 (The current URI for this page, for reference purposes)
  • Depositors only (login required):