Training neural networks using consistency measures
US11544498B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 5, 2021 |
| Grant date | Jan 3, 2023 |
| Priority date | — |
| Expiry date | Jul 2, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/774
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using consistency measures. One of the methods includes processing a particular training example from a mediator training data set using a first neural network to generate a first output for a first machine learning task; processing the particular training example in the mediator training data set using each of one or more second neural networks, wherein each second neural network is configured to generate a second output for a respective second machine learning task; determining, for each second machine learning task, a consistency target output for the first machine learning task; determining, for each second machine learning task, an error between the first output and the consistency target output corresponding to the second machine learning task; and generating a parameter update for the first neural network from the determined errors.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.