Patent · US Active

Neural network method and apparatus with parameter quantization

US11836603B2 · kind B2 · utility

0Cited by
3References
23Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 22, 2019
Grant dateDec 5, 2023
Priority date
Expiry dateApr 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.