Error tolerant neural network model compression
US10229356B1 · kind B1 · utility
142Cited by
0References
19Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 23, 2014 |
| Grant date | Mar 12, 2019 |
| Priority date | — |
| Expiry date | May 23, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Features are disclosed for error tolerant model compression. Such features could be used to reduce the size of a deep neural network model including several hidden node layers. The size reduction in an error tolerant fashion ensures predictive applications relying on the model do not experience performance degradation due to model compression. Such predictive applications include automatic recognition of speech, image recognition, and recommendation engines. Partially quantized models are re-trained such that any degradation of accuracy is “trained out” of the model providing improved error tolerance with compression.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.