Supervised training of a neural network
US5566273A · kind A · utility
22Cited by
9References
14Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 30, 1993 |
| Grant date | Oct 15, 1996 |
| Priority date | — |
| Expiry date | Dec 30, 2013 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY10S128/925
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention provides a system and method for supervised training of a neural network. A neural network architecture and training method is disclosed that is a modification of an ARTMAP architecture. The modified ARTMAP network is an efficient and robust paradigm which has the unique property of incremental supervised learning. Furthermore, the modified ARTMAP network has the capability of removing undesired knowledge that has previously been learned by the network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.