Patent · US Active

Hybrid memory cell unit and recurrent neural network including hybrid memory cell units

US10387769B2 · kind B2 · utility

5Cited by
5References
29Claims
0Family size

Assignees

Inventors

Key dates

Filing dateAug 10, 2017
Grant dateAug 20, 2019
Priority date
Expiry dateAug 18, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A recurrent neural network including an input layer, a hidden layer, and an output layer, wherein the hidden layer includes hybrid memory cell units, each of the hybrid memory cell units including a first memory cells of a first type, the first memory cells being configured to remember a first cell state value fed back to each of gates to determine a degree to which each of the gates is open or closed, and configured to continue to update the first cell state value, and a second memory cells of a second type, each second memory cell of the second memory cells including a first time gate configured to control a second cell state value of the second memory cell based on phase signals of an oscillatory frequency, and a second time gate configured to control an output value of the second memory cell based on the phase signals, and each second memory cell of the second memory cells being configured to remember the second cell state value.

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