Asynchronous neural network training
US11288575B2 · kind B2 · utility
4Cited by
3References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | May 18, 2017 |
| Grant date | Mar 29, 2022 |
| Priority date | — |
| Expiry date | Jul 23, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/098
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.