US 12,468,946 B2
Method and apparatus with neural network parameter quantization
Hyeongseok Yu, Seoul (KR); Hyeonuk Sim, Iksan-si (KR); and Jongeun Lee, Ulsan (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR); and UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY), Ulsan (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR); and UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY), Ulsan (KR)
Filed on Nov. 15, 2022, as Appl. No. 17/987,079.
Application 17/987,079 is a continuation of application No. 16/890,045, filed on Jun. 2, 2020, granted, now 11,531,893.
Claims priority of provisional application 62/856,212, filed on Jun. 3, 2019.
Claims priority of application No. 10-2019-0104581 (KR), filed on Aug. 26, 2019.
Prior Publication US 2023/0085442 A1, Mar. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A processor-implemented method, the method comprising:
determining a first quantization value by performing log quantization on a parameter processed in a layer of a neural network;
comparing a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter; and
quantizing the parameter into two or more quantization values including the first quantization value based on the result of the comparing to avoid degradation of the neural network.