Patent · US Active

Generating parameter values for recurrent neural networks

US11900235B1 · kind B1 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 9, 2021
Grant dateFeb 13, 2024
Priority date
Expiry dateApr 15, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using recurrent neural networks. One of the systems includes a main recurrent neural network comprising one or more recurrent neural network layers and a respective hyper recurrent neural network corresponding to each of the one or more recurrent neural network layers, wherein each hyper recurrent neural network is configured to, at each of a plurality of time steps: process the layer input at the time step to the corresponding recurrent neural network layer, the current layer hidden state of the corresponding recurrent neural network layer, and a current hypernetwork hidden state of the hyper recurrent neural network to generate an updated hypernetwork hidden state.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.