-
公开(公告)号:US20240346312A1
公开(公告)日:2024-10-17
申请号:US18750655
申请日:2024-06-21
Applicant: Samsung Electronics Co., Ltd.
Inventor: Jijoong MOON , Parichay KAPOOR , Jihoon LEE , Hyeonseok LEE , Myungjoo HAM
Abstract: An electronic apparatus may include a memory configured to store data related to a neural network model and at least one processor configured to divide a learning step performed through a plurality of layers of the neural network model into a plurality of steps including a forward propagation step, a gradient calculation step, and a derivative calculation step, and determine an execution order of the plurality of steps, obtain first information regarding in which step of a plurality of steps according to the determined execution order a plurality of sensors used in the plurality of layers are used, based on the determined execution order, integrate the determined execution order based on the first information and second information regarding whether tensors used in neighboring layers from among the plurality of layers are able to be shared, allocate the data to the plurality of tensors by minimizing a region of the memory for allocating data corresponding to the plurality of tensors, based on the integrated execution order, and train the neural network model according to the integrated execution order using the plurality of tensors and the data allocated to the plurality of tensors. Various other embodiments are possible to be implemented.
-
公开(公告)号:US20200074283A1
公开(公告)日:2020-03-05
申请号:US16555331
申请日:2019-08-29
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Parichay KAPOOR , Saehyung LEE , Dongsoo LEE , Byeoungwook KIM
Abstract: An electronic apparatus is provided. The electronic apparatus includes a storage storing a matrix included in an artificial intelligence model, and a processor. The processor divides data included in at least a portion of the matrix by one of rows and columns of the matrix to form groups, clusters the groups into clusters based on data included in each of the groups, and quantizes data divided by the other one of rows and columns of the matrix among data included in each of the clusters.
-
公开(公告)号:US20200234131A1
公开(公告)日:2020-07-23
申请号:US16727323
申请日:2019-12-26
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Dongsoo LEE , Sejung KWON , Parichay KAPOOR , Byeoungwook KIM
Abstract: An electronic apparatus is provided. The electronic apparatus includes sample data and memory storing a first matrix included in an artificial intelligence model trained based on sample data, and a processor configured to prunes each of a plurality of first elements included in the first matrix based on a first threshold, and acquire a first pruning index matrix that indicates whether each of the plurality of first elements has been pruned with binary data, factorize the first matrix to a second matrix of which size was determined based on the number of rows and the rank, and a third matrix of which size was determined based on the rank and the number of columns of the first matrix, prunes each of a plurality of second elements included in the second matrix based on a second threshold, and acquire a second pruning index matrix that indicates whether each of the plurality of second elements has been pruned with binary data, prunes each of a plurality of third elements included in the third matrix based on a third threshold, and acquire a third pruning index matrix that indicates whether each of the plurality of third elements has been pruned with binary data, acquire a final index matrix based on the second pruning index matrix and the third pruning index matrix, and update at least one of the second pruning index matrix or the third pruning index matrix by comparing the final index matrix with the first pruning index matrix.
-
公开(公告)号:US20180357166A1
公开(公告)日:2018-12-13
申请号:US15781316
申请日:2016-12-02
Applicant: Samsung Electronics Co., Ltd.
Inventor: Changhun YU , Wonjin KIM , Hyunsik KIM , Sunho MOON , Minwook AHN , Rakie KIM , Kyoungsoo CHO , Nikunj SAUNSHI , Parichay KAPOOR , Pankaj AGARWAL , Won-Sub KIM , Jin-Hyo KIM , Hyunghoon KIM , Jisu OH , Keongho LEE , Seung-Beom LEE , Jinseok LEE , Dong-Gi JANG , Subin JO , Apoorv KANSAL
IPC: G06F12/06 , G06F12/0882 , G06F12/0817 , G06F12/1009
CPC classification number: G06F12/0646 , G06F12/0822 , G06F12/0882 , G06F12/1009
Abstract: The present disclosure relates to system resource management in a variety of situations. The present disclosure provides a method and an apparatus for reducing memory requirements and improving processing speed when an electronic device performs padding for a particular arithmetic operation on data. To achieve the above objective, a method for operating an electronic device according to the present disclosure comprises the steps of: reading a first portion of data from a first memory; determining a first padding address based on the address of a byte belonging to a boundary region of the data among a plurality of bytes included in the first portion; writing values of the plurality of bytes and a value corresponding to the first padding address to a second memory; and reading a second portion of the data from the first memory.
-
公开(公告)号:US20170109035A1
公开(公告)日:2017-04-20
申请号:US15293757
申请日:2016-10-14
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Pankaj AGARWAL , Sameer Kumar AGRAWAL , Parichay KAPOOR
IPC: G06F3/0488 , G06F21/60 , G06F21/36 , G06F3/0482 , G06F3/0481
CPC classification number: G06F3/04883 , G06F3/0481 , G06F3/0482 , G06F21/36 , G06F21/604 , G06F2221/2133
Abstract: The present disclosure relates generally to technologies for sensor networks, machine-to-machine (M2M), machine-type communication (MTC), and Internet of things (IoT). The present disclosure may be used in intelligent services (smart home, smart building, smart city, smart car, or connected car, health-care, digital education, retail business, security and safety-related services, etc.), or the like, without limitation. According to the present disclosure, a method for locking a device comprises displaying a screen requesting selection of an image category for a lock screen when an input corresponding to a lock request through a display unit supporting a touch input is detected; displaying a screen requesting setting a password for unlocking when an input corresponding to the selection of the image category is detected; and selecting images supporting the password setting among images included in the selected image category into a group when an input corresponding to the password setting is detected, and locking the touch input to the display unit by displaying one of the selected images.
-
公开(公告)号:US20240394750A1
公开(公告)日:2024-11-28
申请号:US18796475
申请日:2024-08-07
Applicant: Samsung Electronics Co., Ltd.
Inventor: Myungjoo HAM , Gichan JANG , Parichay KAPOOR
IPC: G06Q30/0251
Abstract: Disclosed is a client device for personalizing an advertisement, the client device including a memory storing instructions, and a processor, wherein the processor is configured to execute the instructions to obtain, through an advertisement personalization unit, activity information about a user related to the client device, based on an artificial intelligence learning model and the activity information, generate, through the advertisement personalization unit, a personalized advertisement query for the user, transmit, through the advertisement personalization unit, the advertisement query to an advertisement management server, receive, through the advertisement personalization unit, information about at least one advertisement corresponding to the advertisement query, from the advertisement management server, and provide, through the advertisement personalization unit, part or all of the information about the at least one advertisement, to an advertisement output unit.
-
公开(公告)号:US20200373946A1
公开(公告)日:2020-11-26
申请号:US16854285
申请日:2020-04-21
Applicant: Samsung Electronics Co., Ltd.
Inventor: Dongsoo LEE , Sejung KWON , Byeoungwook KIM , Parichay KAPOOR , Baeseong PARK
Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.
-
公开(公告)号:US20170153792A1
公开(公告)日:2017-06-01
申请号:US15290431
申请日:2016-10-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Parichay KAPOOR , Mehul Kumar , Sun-hwa KIM , Jin-sung KIM , Hwakyung Kim , Pankaj AGARWAL
IPC: G06F3/0481 , G06F3/0488 , G06F3/0484
CPC classification number: G06F3/04817 , G06F3/0482 , G06F3/04855 , G06F3/0486 , G06F3/04883 , G06F3/04886 , G06F3/167 , G06F2203/0381
Abstract: A user terminal device includes a touch screen including a main display area and an auxiliary display area including a curved portion extending from the main display area, and a processor configured to, in response to an input for moving an icon displayed on the main display area to the auxiliary display area, control the touch screen to display the icon on the auxiliary display area.
-
公开(公告)号:US20210279589A1
公开(公告)日:2021-09-09
申请号:US17258617
申请日:2019-05-10
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Dongsoo LEE , Parichay KAPOOR , Byeoungwook KIM
Abstract: Disclosed is an electronic device. The electronic device comprises a storage in which sample data and a matrix included in an artificial intelligence model which is trained on the basis of the sample data are stored, and a processor, wherein the processor is configured to: on the basis of the sizes of a plurality of elements included in the matrix, obtain a first matrix pruned by converting values of elements in the number corresponding to a first proportion to zero values; on the basis of test data, obtain first accuracy of an artificial intelligence model including the first matrix; if the first accuracy is within a preset range with respect to a preset value, retrain the artificial intelligence model including the first matrix on the basis of the sample data; and, on the basis of the sizes of a plurality of elements included in the retrained first matrix, obtain a second matrix pruned by converting values of elements in the number corresponding to a second proportion, which is greater than the first proportion, to zero values.
-
公开(公告)号:US20210111741A1
公开(公告)日:2021-04-15
申请号:US17130538
申请日:2020-12-22
Applicant: Samsung Electronics Co., Ltd.
Inventor: Dongsoo LEE , Sejung KWON , Byeoungwook KIM , Parichay KAPOOR , Baeseong PARK
Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.
-
-
-
-
-
-
-
-
-