Efficient mixed-precision search for quantizers in artificial neural networks
US12417389B2 · kind B2 · utility
0Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Nov 20, 2020 |
| Grant date | Sep 16, 2025 |
| Priority date | — |
| Expiry date | Mar 18, 2044 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for performing efficient mixed-precision search for an artificial neural network (ANN) includes training the ANN by sampling selected candidate quantizers of a bank of candidate quantizer and updating network parameters for a next iteration based on outputs of layers of the ANN. The outputs are computed by processing quantized data with operators (e.g., convolution). The quantizers converge to optimal bit-widths that reduce classification losses bounded by complexity constrains.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.