Neural network method and apparatus with parameter quantization
US11836603B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 22, 2019 |
| Grant date | Dec 5, 2023 |
| Priority date | — |
| Expiry date | Apr 7, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/09
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A neural network method of parameter quantization obtains channel profile information for first parameter values of a floating-point type in each channel included in each of feature maps based on an input in a first dataset to a floating-point parameters pre-trained neural network, and determines a probability density function (PDF) type, for each channel, appropriate for the channel profile information based on a classification network receiving the channel profile information as a dataset. The neural network method of parameter quantization determines a fixed-point representation, based on the determined PDF type, for each channel, statistically covering a distribution range of the first parameter values, and generates a fixed-point quantized neural network based on the fixed-point representation determined for each channel.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.