Learning observation representations by predicting the future in latent space
US11568207B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 27, 2019 |
| Grant date | Jan 31, 2023 |
| Priority date | — |
| Expiry date | Jul 2, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network that is configured to process an input observation to generate a latent representation of the input observation. In one aspect, a method includes: obtaining a sequence of observations; for each observation in the sequence of observations, processing the observation using the encoder neural network to generate a latent representation of the observation; for each of one or more given observations in the sequence of observations: generating a context latent representation of the given observation; and generating, from the context latent representation of the given observation, a respective estimate of the latent representations of one or more particular observations that are after the given observation in the sequence of observations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.