Title :
PCN: the probabilistic convergent network
Author :
Howells, G. ; Fairhurst, M.C. ; Bisset, D.L.
Author_Institution :
Electron. Eng. Labs., Kent Univ., Canterbury, UK
Abstract :
A new architecture for networks constructed from RAM-based neurons is presented which, whilst retaining learning and generalisation properties possessed by existing RAM-based network architectures, allows for a regular treatment of specialisation and generalisation with the additional property of providing information regarding the relative probability of a given sample pattern being a member of each possible pattern class. The network architecture provides the basis for the development of a pattern recognition system capable of application in a practical environment
Keywords :
generalisation (artificial intelligence); learning (artificial intelligence); neural nets; pattern recognition; probability; RAM-based neurons; generalisation properties; learning properties; pattern recognition system; probabilistic convergent network; specialisation; Boolean functions; Laboratories; Logic; Neural networks; Neurons; Pattern recognition; Personal communication networks; Visualization;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487326
