PCN: the probabilistic convergent network
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 pr...
Saved in:
Published in | Proceedings of ICNN'95 - International Conference on Neural Networks Vol. 3; pp. 1211 - 1214 vol.3 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
1995
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | 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. |
---|---|
ISBN: | 9780780327689 0780327683 |
DOI: | 10.1109/ICNN.1995.487326 |