公开(公告)号：US20240221374A1

公开(公告)日：2024-07-04

申请号：US18321248

申请日：2023-05-22

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Suhyun KIM ,  Yu-Jin KIM ,  Dogyun PARK

IPC: G06V10/82 ,  G06V10/77

CPC classification number: G06V10/82 ,  G06V10/7715

Abstract: An apparatus and method for generating training data according to an embodiment is disclosed. The apparatus for generating training data according to an embodiment includes at least one processor and a memory to store instructions for executing the at least one processor, wherein upon being executed by the at least one processor, the instructions allow the at least one processor to output a first image for one sample vector from a first generator included in the apparatus, and generate a second image from a second generator included in the apparatus based on the first image and a feature map extracted from a convolution block for each stage of a lightweight target model for the first image.

公开(公告)号：US20230124054A1

公开(公告)日：2023-04-20

申请号：US17964452

申请日：2022-10-12

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Suhyun KIM

IPC: G06N3/04 ,  G06N3/08

Abstract: Embodiments relate to a method and device for generating a neural network that compensates for information loss due to pruning, including obtaining a trained neural network; pruning at least one neuron in the trained neural network; and updating one or more parameter values of a next layer in a pruned neural network based on one or more parameter values of at least one neuron among remaining neurons in a pruned target layer having the pruned neuron.

公开(公告)号：US20180130100A1

公开(公告)日：2018-05-10

申请号：US15802495

申请日：2017-11-03

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Suhyun KIM ,  Gyuwon SONG

IPC: G06Q30/02 ,  G06Q50/16 ,  G06Q50/30 ,  G06Q10/04

CPC classification number: G06Q30/0278 ,  G06Q10/047 ,  G06Q50/16 ,  G06Q50/30

Abstract: A method for evaluating public transportation convenience for real estate according to an embodiment includes determining a plurality of target workplaces, receiving input of real estate information, determining a plurality of public transportation routes corresponding to routes from the inputted real estate to each of the plurality of target workplaces, calculating route scores by workplace, for each of the plurality of public transportation routes, reflecting an objective route element and transportation convenience between the inputted real estate and the target workplace, and a preset workplace weight for each target workplace, and evaluating public transportation convenience by summing up the route scores by workplace for each of the plurality of public transportation routes.