Adjusting automated neural network generation based on evaluation of candidate neural networks
US10410121B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Oct 25, 2017 |
| Grant date | Sep 10, 2019 |
| Priority date | — |
| Expiry date | Oct 25, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes determining, by a processor of a computing device, an expected performance or reliability of a first neural network of a first plurality of neural networks. The expected performance or reliability is determined based on a vector representing at least a portion of the first neural network, where the first neural network is generated based on an automated generative technique (e.g., a genetic algorithm) and where the first plurality of neural networks corresponds to a first epoch of the automated generative technique. The method also includes responsive to the expected performance or reliability of the first neural network failing to satisfy a threshold, adjusting a parameter of the automated generative technique. The method further includes, during a second epoch of the automated generative technique, generating a second plurality of neural networks based at least in part on the adjusted parameter.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.