Adaptive classifier having multiple subnetworks
US5701398A · kind A · utility
87Cited by
1References
13Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 19, 1996 |
| Grant date | Dec 23, 1997 |
| Priority date | — |
| Expiry date | Jul 19, 2016 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network including a plurality of sub-nets stored in a memory array and a method of operation. Each of the sub-nets includes a corresponding plurality of weights and is individually operable to classify an input vector. A computation unit, including a distance calculation unit and a math unit, is responsive to an input vector comprising input training features for determining a distance between the weights of each sub-net to each of the input features of the input vector and for determining whether the distance is within a particular region of influence. Also described is a parallel process for training the sub-nets.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.