Patents by Inventor Yoo-chan Kim

Yoo-chan Kim has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20230409887
    Abstract: Disclosed is a method of compressing a neural network model that is performed by a computing device. The method includes receiving a trained model and compression method instructions for compressing the trained model, identifying a compressible block and a non-compressible block among a plurality of blocks included in the trained model based on the compression method instructions, transmitting a command to a user device that causes the user device to: display a structure of the trained model representing a connection relationship between the plurality of blocks on a first screen such that the compressible block and the non-compressible block are visually distinguished, and display, on a second screen, an input field operable to receive a parameter value entered by a user for compression of the compressible block, and compressing the trained model based on the parameter value entered by the user in the input field.
    Type: Application
    Filed: August 29, 2023
    Publication date: December 21, 2023
    Inventors: Yoo Chan KIM, Jong Won BAEK, Geun Jae LEE
  • Patent number: 11775806
    Abstract: Disclosed is a method of compressing a neural network model that is performed by a computing device. The method includes receiving a trained model and compression method instructions for compressing the trained model, identifying a compressible block and a non-compressible block among a plurality of blocks included in the trained model based on the compression method instructions, transmitting a command to a user device that causes the user device to: display a structure of the trained model representing a connection relationship between the plurality of blocks on a first screen such that the compressible block and the non-compressible block are visually distinguished, and display, on a second screen, an input field operable to receive a parameter value entered by a user for compression of the compressible block, and compressing the trained model based on the parameter value entered by the user in the input field.
    Type: Grant
    Filed: February 2, 2023
    Date of Patent: October 3, 2023
    Assignee: NOTA, INC.
    Inventors: Yoo Chan Kim, Jong Won Baek, Geun Jae Lee
  • Publication number: 20230252292
    Abstract: Disclosed is a method of providing information on a neural network model. The method includes receiving information on a target device and target performance of the neural network model; deriving information on a plurality of candidate neural network models; and transmitting a command to the external device to display information on the plurality of candidate neural network models, wherein the information on the plurality of candidate neural network models includes at least one of name of the plurality of candidate neural network models, performance of the plurality of candidate neural network models, or size of input data of the plurality of candidate neural network models.
    Type: Application
    Filed: February 1, 2023
    Publication date: August 10, 2023
    Inventors: Yoo Chan KIM, Ji Na SHIN, Ho In NA, Chae Hyuk LEE, Dong Wook KIM, Jong Won BAEK, Cheol Bin PARK, Sun Joo PARK
  • Publication number: 20230252274
    Abstract: Disclosed is a method of controlling an electronic apparatus. The method includes receiving a trained model based on a data set and information on a target device, compressing the trained model based on compression configuring information for compression of the trained model, and providing download data corresponding to the compressed trained model so that the compressed trained model may be deployed on the target device.
    Type: Application
    Filed: February 1, 2023
    Publication date: August 10, 2023
    Inventors: Yoo Chan KIM, Jong Won BAEK, Steven KIM, Myung Su CHAE
  • Publication number: 20230252293
    Abstract: Disclosed is a method of compressing a neural network model that is performed by a computing device. The method includes receiving a trained model and compression method instructions for compressing the trained model, identifying a compressible block and a non-compressible block among a plurality of blocks included in the trained model based on the compression method instructions, transmitting a command to a user device that causes the user device to: display a structure of the trained model representing a connection relationship between the plurality of blocks on a first screen such that the compressible block and the non-compressible block are visually distinguished, and display, on a second screen, an input field operable to receive a parameter value entered by a user for compression of the compressible block, and compressing the trained model based on the parameter value entered by the user in the input field.
    Type: Application
    Filed: February 2, 2023
    Publication date: August 10, 2023
    Inventors: Yoo Chan KIM, Jong Won BAEK, Geun Jae LEE
  • Patent number: 9990162
    Abstract: An operating method of a memory controller may include: enabling a security mode in response to a first command received from a host; generating a security key based on a host key received from the host; storing the security key in a security key storing unit; and/or performing a first data processing operation of encrypting data received from the host and decrypting data stored in a non-volatile memory device, based on the security key, when the security mode is enabled. The security key storing unit may be a volatile memory.
    Type: Grant
    Filed: December 3, 2015
    Date of Patent: June 5, 2018
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Ji-soo Kim, Yoo-chan Kim, Moon-sang Kwon
  • Publication number: 20160191235
    Abstract: An operating method of a memory controller may include: enabling a security mode in response to a first command received from a host; generating a security key based on a host key received from the host; storing the security key in a security key storing unit; and/or performing a first data processing operation of encrypting data received from the host and decrypting data stored in a non-volatile memory device, based on the security key, when the security mode is enabled. The security key storing unit may be a volatile memory.
    Type: Application
    Filed: December 3, 2015
    Publication date: June 30, 2016
    Inventors: Ji-soo Kim, Yoo-chan Kim, Moon-Sang Kwon