Continuous learning of simulation trained deep neural network model
US11315015B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 8, 2018 |
| Grant date | Apr 26, 2022 |
| Priority date | — |
| Expiry date | Feb 2, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention provides a system and method of side-stepping the need to retrain neural network model after initially trained using a simulator by comparing real-world data to data predicted by the simulator for the same inputs, and developing a mapping correlation that adjusts real world data toward the simulation data. Thus, the decision logic developed in the simulation-trained model is preserved and continues to operate in an altered reality. A threshold metric of similarity can be initially provided into the mapping algorithm, which automatically adjusts real world data to adjusted data corresponding to the simulation data for operating the neural network model when the metric of similarity between the real world data and the simulation data exceeds the threshold metric. Updated learning can continue as desired, working in the background as conditions are monitored.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.