Howells, Gareth and Fairhurst, Michael and Bisset, D.L. (1995) GCN: The Generalised Convergent Network. In: Fifth International Conference on Image Processing and its Applications, 1995. International Conference on Image Processing and its Applications . IEEE. ISBN 0-85296-642-3. (doi:10.1049/cp:19950735) (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:59319)
| 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: http://www.dx.doi.org/10.1049/cp:19950735 |
|
Abstract
A new architecture for networks of RAM-based Boolean neurons is presented which, whilst retaining learning and generalisation properties possessed by existing network architectures, allows for a regular treatment of specialisation and generalisation with strong convergence properties. The network architecture provides the basis for a pattern recognition system capable of application in a practical environment.
| Item Type: | Book section |
|---|---|
| DOI/Identification number: | 10.1049/cp:19950735 |
| Uncontrolled keywords: | Boolean algebra, Artificial intelligence, Learning systems, Neural network architecture, Pattern recognition, Random access memories |
| Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks |
| Institutional Unit: | Schools > School of Engineering, Mathematics and Physics > Engineering |
| Former Institutional Unit: |
Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
|
| Depositing User: | Gareth Howells |
| Date Deposited: | 30 Nov 2016 19:09 UTC |
| Last Modified: | 20 May 2025 10:41 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/59319 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):

https://orcid.org/0000-0001-5590-0880
Altmetric
Altmetric