Model building for simulation of one or more target features
US10402726B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 3, 2018 |
| Grant date | Sep 3, 2019 |
| Priority date | — |
| Expiry date | May 3, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving an input data set, each entry including multiple features. The method includes receiving a user input identifying a target feature of the multiple features and a target value of the target feature. The method includes determining, one or more correlated features of the multiple features. The method includes providing the input data set to multiple neural networks (including multiple VAEs) to train the multiple neural networks. The method includes generating a simulated data set based on the input data set, each entry including at least the target feature and the one or more correlated features. Values of the one or more correlated features are randomized or pseudorandomized and the target feature is fixed at the target value. The method includes providing the simulated data set to the multiple neural networks to generate output data and displaying a GUI based on the output data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.