公开(公告)号：US20250139422A1

公开(公告)日：2025-05-01

申请号：US18919294

申请日：2024-10-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shanshan LV ,  Jonghoon YOON ,  Byung In YOO ,  Changyong SON ,  Sung-Jae CHO ,  Yunhao ZHANG ,  Zhenxin YANG ,  Miao ZHANG

IPC: G06N3/0495

Abstract: A method performed by one or more processors includes: iteratively training layer-specific quantization levels and layer-specific quantization intervals of respective layers of a neural network of original weights by, for each training iteration, adjusting the quantization levels and quantization intervals to reduce a loss that is determined based on the original weights and is determined based on the original weights as quantized according to the quantization levels and quantization intervals at a current iteration of the training.

公开(公告)号：US20240242090A1

公开(公告)日：2024-07-18

申请号：US18477139

申请日：2023-09-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sung-Jae CHO ,  Changyong SON ,  Jongseok KIM ,  Jonghoon YOON

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: A method of searching for hyperparameters for neural network learning includes: obtaining a preset early stop point; determining whether a current trial, among trials for searching for different combinations of hyperparameters, corresponds to a dry run trial; in response to a determination that the current trial corresponds to a dry run trial: executing learning epochs belonging to the current trial; searching for a combination of hyperparameters assigned to the current trial according to a result of the executing of the learning epochs; and changing the early stop point by based on whether an early stop with respect to a found combination of the hyperparameters is a success in each of the learning epochs.

公开(公告)号：US20220301188A1

公开(公告)日：2022-09-22

申请号：US17385455

申请日：2021-07-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jonghoon YOON ,  Dongwook LEE ,  Changyong SON ,  Byung In YOO ,  Seohyung LEE

IPC: G06T7/246 ,  G06K9/62 ,  H04N5/232

Abstract: A processor-implemented method of tracking a target object includes: extracting a feature from frames of an input image; selecting one a neural network model from among a plurality of neural network models that is provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.

公开(公告)号：US20240256895A1

公开(公告)日：2024-08-01

申请号：US18343073

申请日：2023-06-28

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Korea Advanced Institute of Science and Technology

Inventor： Jonghoon YOON ,  Geon PARK ,  Jaehong YOON ,  Sung Ju HWANG ,  Wonyong JEONG

IPC: G06N3/098 ,  G06N3/045

CPC classification number: G06N3/098 ,  G06N3/045

Abstract: A method and device with federated learning of neural network models are disclosed. A method includes: receiving weights of respective clients, wherein each weight has a respectively corresponding precision that is initially an inherent precision; using a dequantizer to change the weights such that the precisions thereof are changed from the inherent precisions to a same reference precision; determining masks respectively corresponding to the weights based on the inherent precisions; based on the masks, determining an integrated weight by merging the weights having the reference precision; and quantizing the integrated weight to generate quantized weights having the inherent precisions, respectively, and transmitting the quantized weights to the clients.

公开(公告)号：US20240184625A1

公开(公告)日：2024-06-06

申请号：US18480924

申请日：2023-10-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jongseok KIM ,  Youngmin KIM ,  Jonghoon YOON ,  SUNG-JAE CHO ,  Changyong SON

IPC: G06F9/48

CPC classification number: G06F9/4881

Abstract: A method of a system including a processor including recording experiment information of a job in connection with job information generated based on an execution of a job of a computer cluster system, and controlling further execution of a job, by the computer cluster system, by transmitting a change in the experiment information to the computer cluster system based on the job information.