Patent · US Active

Neural architecture search

US11030523B2 · kind B2 · utility

4Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 29, 2019
Grant dateJun 8, 2021
Priority date
Expiry dateApr 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.