Methods for updating and training for a self-organising card
US8510243B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Dec 12, 2008 |
| Grant date | Aug 13, 2013 |
| Priority date | — |
| Expiry date | Jan 20, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/088
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The updating method comprises selecting the best winning neuron and second best winning neuron, modifying the prototype vectors of the best winning neuron and the neurons located around the best winning neuron in the direction of the vector of the learning point (x(k)), determining the neighboring neurons (N(u*)) of the best winning neuron (u*) and, if the second best winning neuron (u**) is part of the neighboring neurons (N(u*)), increasing the valuation of the connection between the first and second best winning neurons.The updating method further involves reducing the valuation of each connection between the first best winning neuron and the direct neighboring neurons (N(u*)) other than the second best winning neuron (u**).
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.