Patent · US Active

Regularization of recurrent machine-learned architectures with encoder, decoder, and prior distribution

US12106220B2 · kind B2 · utility

2Cited by
2References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 7, 2019
Grant dateOct 1, 2024
Priority date
Expiry dateSep 21, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

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