Asynchronous parameter aggregation for machine learning
US11373115B2 · kind B2 · utility
4Cited by
3References
21Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 9, 2018 |
| Grant date | Jun 28, 2022 |
| Priority date | — |
| Expiry date | Apr 29, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19167
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods are provided for training a machine learned model on a large number of devices, each device acquiring a local set of training data without sharing data sets across devices. The devices train the model on the respective device's set of training data. The devices communicate a parameter vector from the trained model asynchronously with a parameter server. The parameter server updates a master parameter vector and transmits the master parameter vector to the respective device.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.