Methods and systems for training convolutional neural network using built-in attention
US11403486B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 11, 2020 |
| Grant date | Aug 2, 2022 |
| Priority date | — |
| Expiry date | Dec 19, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19173
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems for updating the weights of a set of convolution kernels of a convolutional layer of a neural network are described. A set of convolution kernels having attention-infused weights is generated by using an attention mechanism based on characteristics of the weights. For example, a set of location-based attention multipliers is applied to weights in the set of convolution kernels, a magnitude-based attention function is applied to the weights in the set of convolution kernels, or both. An output activation map is generated using the set of convolution kernels with attention-infused weights. A loss for the neural network is computed, and the gradient is back propagated to update the attention-infused weights of the convolution kernels.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.