-
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:US20230144680A1
公开(公告)日:2023-05-11
申请号:US17437320
申请日:2020-11-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Jijoong MOON , Wook SONG , Sangjung WOO , Geunsik LIM , Jaeyun JUNG , Myungjoo HAM
IPC: G06F21/60 , G06N3/08 , G06N3/0464
CPC classification number: G06F21/602 , G06N3/08 , G06N3/0464
Abstract: An electronic apparatus and a method for controlling thereof are provided. The electronic apparatus includes a memory storing an artificial neural network and metadata including information of at least one layer in the artificial neural network, and a processor configured to: acquire a security vector based on the metadata and a security key of the electronic apparatus; map the security vector and the metadata with the security key and identification information of the artificial neural network; perform encryption on the at least one layer based on the metadata and the security vector; based on input data input to the artificial neural network, load the metadata and the security vector by using the security key and the identification information of the artificial neural network; and perform an operation between the input data and the encrypted at least one layer based on the loaded security vector and the metadata.
-
公开(公告)号:US20210319282A1
公开(公告)日:2021-10-14
申请号:US17266781
申请日:2019-10-04
Applicant: Samsung Electronics Co., Ltd.
Inventor: Myungjoo HAM , Jijoong MOON , Jinhyuck PARK , Hyoungjoo AHN , Geunsik LIM , Jaeyun JUNG
IPC: G06N3/04
Abstract: The disclosure provides an electronic device and a method for controlling same. The electronic device comprises: a memory; and a processor, connected to the memory, for controlling the electronic device, wherein the processor executes at least one command stored in the memory, and is thereby capable of controlling scheduling of data processing of a plurality of artificial intelligence models on the basis of at least one of a data processing speed and a connection structure of the plurality of artificial intelligence models.
-
公开(公告)号:US20230214122A1
公开(公告)日:2023-07-06
申请号:US18088087
申请日:2022-12-23
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Geunsik LIM , Myungjoo HAM
IPC: G06F3/06
CPC classification number: G06F3/0611 , G06F3/0644 , G06F3/0679
Abstract: A memory management method or an electronic device for managing memory is provided. The method may include checking available capacity to allocate new process to first memory. The method may include determining whether to swap out the page of the first process to the first memory or the second memory, based on the available capacity and characteristics of the first process that is running in the first memory. The method may include allocating, as a swap space, a partial region of the first memory or the second memory that is determined. The method may include swapping out the page of the first process from the first memory to the swap space. The method may include identifying whether the swapped-out page is swapped-in from the swap space to the first memory. The method may include releasing the swap space.
-
公开(公告)号:US20200341752A1
公开(公告)日:2020-10-29
申请号:US16855314
申请日:2020-04-22
Applicant: Samsung Electronics Co., Ltd.
Inventor: Geunsik LIM , Myungjoo HAM , Jijoong MOON , Wook SONG
Abstract: An electronic apparatus for automatically performing a source code review and a method thereof are provided. The electronic apparatus includes a communication interface, a memory storing at least one instruction, and at least one processor to control the communication interface. The at least one processor, by executing the at least one instruction, is configured to, based on a source code being submitted to a source code repository with a pull request, receive a webhook event message from the source code repository through the communication interface, download the submitted source code from the source code repository, extract a changed source code among the downloaded source codes, and perform a code review of the extracted source code through at least one inspection module.
-
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.
-
7.
公开(公告)号:US20230336605A1
公开(公告)日:2023-10-19
申请号:US18333042
申请日:2023-06-12
Applicant: Samsung Electronics Co., Ltd.
Inventor: Grzegorz Pawel GRZESIAK , Jan KIENIG , Przemyslaw WYSZKOWSKI , Adam KMIEC , Rafal KUC , Myungjoo HAM , Pawel WASOWSKI
Abstract: The disclosure relates to the 5th generation (5G) or 6th generation (6G) communication system to support a high data transmission rate than before. A method of operating a streaming service client (SSC) node in a wireless communication system is provided. The method includes an operation of establishing a connection to a streaming service provider (SSP) via two types of services that are enhanced mobile broadband (eMBB) and ultra reliable low latency communication (URLLC), an operation of receiving first data from the SSP via the eMBB, and simultaneously receiving second data via the URLLC, wherein the second data is metadata of the first data, and operation of determining whether the first data is successfully received, and an operation of producing a data stream using the second data in a case in which the first data is not successfully received.
-
公开(公告)号:US20230171444A1
公开(公告)日:2023-06-01
申请号:US18074878
申请日:2022-12-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Grzegorz Pawel GRZESIAK , Myungjoo HAM , Pawel Wasowski
IPC: H04N21/235
CPC classification number: H04N21/2353
Abstract: A method, performed by a server, of streaming image content, including obtaining one or more frames of the image content which is currently being executed by an electronic device; identifying a plurality of possible user inputs corresponding to the one or more frames; generating a plurality of prediction frame sets respectively corresponding to the plurality of possible user inputs, wherein each prediction frame set of the plurality of prediction frame sets includes a plurality of prediction frames to be displayed after the one or more frames; obtaining metadata from the one or more frames and the plurality of prediction frame sets; generating streaming data of the image content to be provided to the electronic device, based on at least one the plurality of prediction frame sets or the metadata; and transmitting the generated streaming data to the electronic device.
-
公开(公告)号:US20210073634A1
公开(公告)日:2021-03-11
申请号:US17013375
申请日:2020-09-04
Applicant: Samsung Electronics Co., Ltd.
Inventor: Geunsik LIM , Myungjoo HAM , Jaeyun JUNG
Abstract: A server is provided. The server according to the disclosure includes a memory and a processor. The processor is configured to obtain input data to be input to a trained neural network model using a peripheral device handler, obtain output data by inputting the obtained input data to the trained neural network model via a virtual input device generated by the peripheral device handler, store the output data in a memory area assigned to a virtual output device generated by the peripheral device handler, and verify the neural network model based on the output data stored in the memory area assigned to the virtual output device.
-
-
-
-
-
-
-
-