Title :
GCN: the generalised convergent network
Author :
Howells, G. ; Fairhurst, M.C. ; Bisset, D.L.
Author_Institution :
Kent Univ., Canterbury, UK
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
Keywords :
Boolean algebra; generalisation (artificial intelligence); learning (artificial intelligence); neural net architecture; pattern recognition; random-access storage; GCN; RAM-based Boolean neurons; generalisation; generalised convergent network; learning properties; pattern recognition system; specialisation; strong convergence properties;
Conference_Titel :
Image Processing and its Applications, 1995., Fifth International Conference on
Conference_Location :
Edinburgh
Print_ISBN :
0-85296-642-3
DOI :
10.1049/cp:19950735
