Fusing sparse kernels to approximate a full kernel of a convolutional neural network
US10740659B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 14, 2017 |
| Grant date | Aug 11, 2020 |
| Priority date | — |
| Expiry date | Oct 30, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques facilitating generation of a fused kernel that can approximate a full kernel of a convolutional neural network are provided. In one example, a computer-implemented method comprises determining a first pattern of samples of a first sample matrix and a second pattern of samples of a second sample matrix. The first sample matrix can be representative of a sparse kernel, and the second sample matrix can be representative of a complementary kernel. The first pattern and second pattern can be complementary to one another. The computer-implemented method also comprises generating a fused kernel based on a combination of features of the sparse kernel and features of the complementary kernel that are combined according to a fusing approach and training the fused kernel.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.