GCN: the Generalised Convergent Network
GCN: the Generalised Convergent Network
- Author(s): G. Howells ; M.C. Fairhurst ; D.L. Bisset
- DOI: 10.1049/cp:19950735
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Fifth International Conference on Image Processing and its Applications — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): G. Howells ; M.C. Fairhurst ; D.L. Bisset Source: Fifth International Conference on Image Processing and its Applications, 1995 p. 627 – 631
- Conference: Fifth International Conference on Image Processing and its Applications
- DOI: 10.1049/cp:19950735
- ISBN: 0 85296 642 3
- Location: Edinburgh, UK
- Conference date: 4-6 July 1995
- Format: PDF
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.
Inspec keywords: pattern recognition; neural net architecture; generalisation (artificial intelligence); random-access storage; Boolean algebra; learning (artificial intelligence)
Subjects: Neural computing techniques; Parallel architecture; Neural nets (theory); Pattern recognition; Adaptive system theory; Digital storage
Related content
content/conferences/10.1049/cp_19950735
pub_keyword,iet_inspecKeyword,pub_concept
6
6