-
公开(公告)号:US20220237513A1
公开(公告)日:2022-07-28
申请号:US17587291
申请日:2022-01-28
Applicant: Samsung Electronics Co., Ltd.
Inventor: Wenlong HE , Ihor VASYLTSOV , Gang SUN , Duanhui LIU
Abstract: A method with quantization for a deep learning model includes: determining a second model by quantizing a first model based on a quantization parameter; determining a real value of multi optimization target parameter by testing the second model; calculating a loss function based on the real value of the multi optimization target parameter, an expected value of the multi optimization target parameter, and a constraint value of the multi optimization target parameter; updating the quantization parameter based on the loss function and using the second model as the first model; iteratively executing the foregoing operations until a preset condition is satisfied; and in response to the preset condition being satisfied, determining an optimal quantization parameter and using, as a final quantization model, the first model that executes quantization based on the optimal quantization parameter.
-
公开(公告)号:US20240411516A1
公开(公告)日:2024-12-12
申请号:US18734138
申请日:2024-06-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Penghui WEI , Gang SUN , Jiao WU , Hyeonuk SIM
IPC: G06F7/523
Abstract: A precision allocation method and device based on a neural network processor are provided. The precision allocation method includes allocating a weight of a neural network to a multiplier column of a neural network processor, determining a lower tolerance for the multiplier column, and selecting a first data type for the multiplier column from a plurality of data types based on the lower tolerance, wherein each of the plurality of data types corresponds to a different precision level, and performing, by the neural network processor, a multiplication operation based on the weight and the first data type.
-
公开(公告)号:US20240136024A1
公开(公告)日:2024-04-25
申请号:US18480190
申请日:2023-10-03
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Lun YAO , Jiali PANG , Ihor VASYLTSOV , Gang SUN , Zhen ZHANG
IPC: G16C10/00
CPC classification number: G16C10/00
Abstract: A processor-implemented method with molecular dynamics simulation includes: setting a precision of first data used for a molecular dynamics simulation to be a first precision; setting a precision of second data used for the molecular dynamics simulation to be a second precision that is different from the first precision; and conducting the molecular dynamics simulation based on the first data of the first precision and the second data of the second precision.
-
公开(公告)号:US20220207361A1
公开(公告)日:2022-06-30
申请号:US17552501
申请日:2021-12-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Jiali PANG , Gang SUN , Lin CHEN , Zhen Zhang
IPC: G06N3/08
Abstract: A neural network model quantization method and apparatus is provided. The neural network model quantization method includes receiving a neural network model, calculating a quantization parameter corresponding to an operator of the neural network model to be quantized based on bisection approximation, and quantizing the operator to be quantized based on the quantization parameter and obtaining a neural network model having the quantized operator.
-
-
-