Incorporating black-box functions in neural networks
US11481619B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 10, 2019 |
| Grant date | Oct 25, 2022 |
| Priority date | — |
| Expiry date | Jul 11, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for incorporating a black-box function into a neural network are described. For example, an image editing function may be the black-box function and may be wrapped into a layer of the neural network. A set of parameters and a source image are provided to the black-box function, and the output image that represents the source image with the set of parameters applied to the source image is output from the black-box function. To address the issue that the black-box function may not be differentiable, a loss optimization may calculate the gradients of the function using, for example, a finite differences calculation, and the gradients are used to train the neural network to ensure the output image is representative of an expected ground truth image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.