公开(公告)号：US11627383B2

公开(公告)日：2023-04-11

申请号：US17046494

申请日：2019-03-27

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION

Inventor： Sunghyun Kim ,  Yongdeok Kim ,  Gunhee Kim ,  Joonil Na ,  Jinyoung Sung ,  Youngjae Yu ,  Sangho Lee

IPC: H04N21/8549 ,  G06F16/55 ,  G06F16/583 ,  G06F16/58 ,  G06N3/08 ,  H04N21/8547

Abstract: Provided are an electronic device and an operation method thereof. The electronic device includes a memory that stores one or more instructions, and a processor that executes the one or more instructions stored in the memory, wherein the processor is configured to execute the one or more instructions to: divide original image data into a plurality of image sequences; determine a predetermined number of image sequences among the plurality of image sequences as an input image group, select one of the image sequences included in the input image group and add the selected image sequence to the highlight image group based on one or more image sequences pre-classified as a highlight image group, by using a trained model trained using an artificial intelligence algorithm; and generate summary image data extracted from the original image data, by using the image sequence included in the highlight image group.

公开(公告)号：US11481608B2

公开(公告)日：2022-10-25

申请号：US16909095

申请日：2020-06-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sangwon Ha ,  Gunhee Kim ,  Donghyun Lee

IPC: G06N3/04 ,  G06F17/18 ,  G06K9/62

Abstract: A processor-implemented neural network method includes: determining a respective probability density function (PDF) of normalizing a statistical distribution of parameter values, for each channel of each of a plurality of feature maps of a pre-trained neural network; determining, for each channel, a corresponding first quantization range for performing quantization of corresponding parameter values, based on a quantization error and a quantization noise of the respective determined PDF; determining, for each channel, a corresponding second quantization range, based on a signal-to-quantization noise ratio (SQNR) of the respective determined PDF; correcting, for each channel, the corresponding first quantization range based on the corresponding second quantization range; and generating a quantized neural network, based on the corrected first quantization range corresponding for each channel.

公开(公告)号：US11868428B2

公开(公告)日：2024-01-09

申请号：US17340134

申请日：2021-06-07

Applicant: Samsung Electronics Co., Ltd. ,  Seoul National University R&DB Foundation

Inventor： Seon Min Rhee ,  Jaekyeom Kim ,  Gunhee Kim ,  Minjung Kim ,  Dongyeon Woo ,  Seungju Han

IPC: G06V10/40 ,  G06F18/211 ,  G06N3/08 ,  G06F21/34 ,  G06F18/22 ,  G06F18/214 ,  G06V10/74 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06F18/211 ,  G06F18/214 ,  G06F18/22 ,  G06F21/34 ,  G06N3/08 ,  G06V10/40 ,  G06V10/74 ,  G06V10/774 ,  G06V10/82 ,  G06V40/172

Abstract: A neural network includes a drop layer configured to drops feature values. A method of computation using the neural network includes extracting feature data from input data using a first portion of a neural network, generating compressed representation data of the extracted feature data by dropping a feature value from the extracted feature data at a drop layer of the neural network based on a drop probability corresponding to the feature value, and indicating an inference result from the compressed representation data using a second portion of the neural network.

公开(公告)号：US11816557B2

公开(公告)日：2023-11-14

申请号：US17950342

申请日：2022-09-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sangwon Ha ,  Gunhee Kim ,  Donghyun Lee

IPC: G06N3/00 ,  G06N3/063 ,  G06F17/18 ,  G06F18/10 ,  G06F18/2321 ,  G06N3/047 ,  G06V10/764

CPC classification number: G06N3/063 ,  G06F17/18 ,  G06F18/10 ,  G06F18/2321 ,  G06N3/047 ,  G06V10/764

Abstract: A processor-implemented neural network method includes: determining a respective probability density function (PDF) of normalizing a statistical distribution of parameter values, for each channel of each of a plurality of feature maps of a pre-trained neural network; determining, for each channel, a corresponding first quantization range for performing quantization of corresponding parameter values, based on a quantization error and a quantization noise of the respective determined PDF; determining, for each channel, a corresponding second quantization range, based on a signal-to-quantization noise ratio (SQNR) of the respective determined PDF; correcting, for each channel, the corresponding first quantization range based on the corresponding second quantization range; and generating a quantized neural network, based on the corrected first quantization range corresponding for each channel.