Regularization of recurrent machine-learned architectures with encoder, decoder, and prior distribution
US12106220B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 7, 2019 |
| Grant date | Oct 1, 2024 |
| Priority date | — |
| Expiry date | Sep 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.