Neural architecture search
US11030523B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 29, 2019 |
| Grant date | Jun 8, 2021 |
| Priority date | — |
| Expiry date | Apr 29, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0985
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective architecture of a child neural network that is configured to perform a particular neural network task; for each output sequence in the batch: training a respective instance of the child neural network having the architecture defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.