Patent · US Active

Memory augmented generative temporal models

US10872299B2 · kind B2 · utility

9Cited by
6References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 1, 2019
Grant dateDec 22, 2020
Priority date
Expiry dateJul 1, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.

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