Multi-iteration compression for deep neural networks
US10762426B2 · kind B2 · utility
3Cited by
1References
16Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 26, 2016 |
| Grant date | Sep 1, 2020 |
| Priority date | — |
| Expiry date | Dec 19, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A multi-iteration method for compressing a deep neural network into a sparse neural network without degrading the accuracy is disclosed herein. In an example, the method includes determining a respective initial compression ratio for each of a plurality of matrices characterizing the weights between the neurons of the neural network, compressing each of the plurality of matrices based on the respective initial compression ratio, so as to obtain a compressed neural network, and fine-tuning the compressed neural network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.