Masked model training of a prediction network
US11902628B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 13, 2021 |
| Grant date | Feb 13, 2024 |
| Priority date | — |
| Expiry date | Aug 25, 2041 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N21/466
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.