Method and device for deep neural network compression
US12314857B2 · kind B2 · utility
0Cited by
4References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 27, 2021 |
| Grant date | May 27, 2025 |
| Priority date | — |
| Expiry date | Mar 28, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F7/491
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for deep neural network compression is provided. The method includes: using at least one weight of a deep neural network (DNN), setting a value of a P parameter, and combining every P weights in groups, and perform branch pruning and retraining, so that only one of each group has a non-zero weight, and the remaining weights are 0, wherein the remaining weights are evenly divided into branches to adjust a compression rate of the DNN and to adjust a reduction rate of the DNN.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.