Method and apparatus with neural network parameter quantization
US11948074B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 30, 2019 |
| Grant date | Apr 2, 2024 |
| Priority date | — |
| Expiry date | Sep 5, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed is a processor-implemented data processing method in a neural network. A data processing apparatus includes at least one processor, and at least one memory configured to store instructions to be executed by the processor and a neural network, wherein the processor is configured to, based on the instructions, input an input activation map into a current layer included in the neural network, output an output activation map by performing a convolution operation between the input activation map and a weight quantized with a first representation bit number of the current layer, and output a quantized activation map by quantizing the output activation map with a second representation bit number based on an activation quantization parameter.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.