Reducing computations in a neural network
US10460230B2 · kind B2 · utility
17Cited by
9References
14Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Feb 3, 2016 |
| Grant date | Oct 29, 2019 |
| Priority date | — |
| Expiry date | Apr 27, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/082
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Reducing computations in a neural network may include determining a group including a plurality of convolution kernels of a convolution stage of a neural network. The convolution kernels of the group are similar to one another. A base convolution kernel for the group may be determined. Scaling factors for a plurality of input feature maps processed by the group may be calculated. The convolution stage of the neural network may be modified to calculate a composite input feature map using the scaling factors and apply the base convolution kernel to the composite input feature map.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.