Title:
ニューラルネットワーク量子化のための方法及び装置
Document Type and Number:
Japanese Patent JP7329455
Kind Code:
B2
Abstract:
According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.
Inventors:
李 ▲うぉん▼祚
Seungwon Lee
Toshiyuki Lee
Seungwon Lee
Toshiyuki Lee
Application Number:
JP2020002058A
Publication Date:
August 18, 2023
Filing Date:
January 09, 2020
Export Citation:
Assignee:
Samsung Electronics Co.,Ltd.
International Classes:
G06N3/0495
Domestic Patent References:
| JP2018124681A |
Foreign References:
| US20170323197 | ||||
| US20180197081 |
Other References:
Jun Haeng Lee et al.,Quantization for Rapid Deployment of Deep Neural Networks,arXiv [online],2018年,[2023年7月11日検索]、インターネット
Attorney, Agent or Firm:
Tadashige Ito
Tadahiko Ito
Shinsuke Ohnuki
Tadahiko Ito
Shinsuke Ohnuki