中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.019 seconds)

    Graph upscaling method for preserving graph properties
    1.
    发明授权
    Graph upscaling method for preserving graph properties 有权

    公开(公告)号：US11107187B2

    公开(公告)日：2021-08-31

    申请号：US16541628

    申请日：2019-08-15

    Applicant: DAEGU GYEONGBUK INSTITUTE OF SCIENCE AND TECHNOLOGY

    Inventor： Min Soo Kim ,  Himchan Park

    IPC: G06T3/40 ,  G06T1/20 ,  G06F16/901

    Abstract: A graph upscaling method and apparatus is disclosed. The graph upscaling apparatus may store, in a main memory, original graph data including topological data including a vertex and an edge, determine a parent edge using a hash function and the original graph data, and generate a new edge based on the determined parent edge. The graph upscaling apparatus may store, in a main memory, original graph data including topological data including a vertex and an edge, allocate identities (IDs) of edges to be generated to cores included in a central processing unit (CPU) based on the number of the cores, and generate new edges based on the IDs of the edges using a hash function and the original graph data.

    System and method for processing large-scale graphs using GPUs
    3.
    发明授权
    System and method for processing large-scale graphs using GPUs 有权

    公开(公告)号：US10089705B2

    公开(公告)日：2018-10-02

    申请号：US14658325

    申请日：2015-03-16

    Applicant: Daegu Gyeongbuk Institute of Science and Technology

    Inventor： Min Soo Kim ,  Hyun Seok Seo ,  Jin Wook Kim

    IPC: G06T1/20 ,  G06T1/60 ,  G06F17/10

    Abstract: The present invention relates to a system and method for processing a large scale graph using GPUs, and more particularly, to a system and method capable of processing larger-scale graph data beyond the capacity of device memory of GPUs using a streaming method. A large-scale graph processing system using GPUs according to an aspect of the present invention includes a main memory, device memories of a plurality of GPUs that process graph data transferred from the main memory; a loop controller that processes graph data transfer in a nested loop join scheme in the graph data transfer between the main memory and the device memory of the GPU, and a streaming controller that copies the graph data to the device memory of the GPU in a chunk or streaming manner using a GPU stream according to the nested loop join scheme.

    GPU-based artificial intelligence system using channel-level architecture search for deep neural network
    4.
    发明授权
    GPU-based artificial intelligence system using channel-level architecture search for deep neural network 有权

    公开(公告)号：US11687784B2

    公开(公告)日：2023-06-27

    申请号：US16281582

    申请日：2019-02-21

    Applicant: Daegu Gyeongbuk Institute of Science and Technology

    Inventor： Hee Chul Lim ,  Min Soo Kim

    IPC: G06N3/082 ,  G06N3/063

    CPC classification number: G06N3/082 ,  G06N3/063

    Abstract: An artificial intelligence system and a method for searching for an optimal model are provided. A method for searching for a learning mode of an artificial intelligence system includes receiving, by an operator included in a first node, first channels, deriving, by the operator included in the first node, first parameter weight indexes corresponding to weights of first parameters by calculating the first parameters corresponding to each of the received first channels with the received first channels, generating and outputting a second channel group by combining the first channel with the other channel, receiving, by an operator included in a second node, second channels included in the second channel group, and deriving, by the operator included in the second node, second parameter weight indexes corresponding to weights of second parameters by calculating the second parameters corresponding to the received second channels with the received second channels.

    GRAPH UPSCALING METHOD FOR PRESERVING GRAPH PROPERTIES
    5.
    发明申请
    GRAPH UPSCALING METHOD FOR PRESERVING GRAPH PROPERTIES 审中-公开

    公开(公告)号：US20200065939A1

    公开(公告)日：2020-02-27

    申请号：US16541628

    申请日：2019-08-15

    Applicant: DAEGU GYEONGBUK INSTITUTE OF SCIENCE AND TECHNOLOGY

    Inventor： Min Soo Kim ,  Himchan PARK

    IPC: G06T3/40 ,  G06T1/20

    Abstract: A graph upscaling method and apparatus is disclosed. The graph upscaling apparatus may store, in a main memory, original graph data including topological data including a vertex and an edge, determine a parent edge using a hash function and the original graph data, and generate a new edge based on the determined parent edge. The graph upscaling apparatus may store, in a main memory, original graph data including topological data including a vertex and an edge, allocate identities (IDs) of edges to be generated to cores included in a central processing unit (CPU) based on the number of the cores, and generate new edges based on the IDs of the edges using a hash function and the original graph data.

    Graph generating method and apparatus
    7.
    发明授权
    Graph generating method and apparatus 有权

    公开(公告)号：US10593080B2

    公开(公告)日：2020-03-17

    申请号：US15955914

    申请日：2018-04-18

    Applicant: Daegu Gyeongbuk Institute of Science and Technology

    Inventor： Min Soo Kim ,  Himchan Park

    IPC: G06T11/20 ,  G06F17/18 ,  G06F17/16 ,  G06F17/10

    Abstract: Disclosed is a graph generating method and apparatus, the graph generating apparatus that may recognize one source vertex among a plurality of vertices, obtain the target number of at least one edge to generate from the source vertex, among the total target number of edges to generate between the vertices, obtain a recursive vector to be used repeatedly to generate the at least one edge, in a scope in which an existence of an edge for the source vertex needs to be verified, and generate the at least one edge between the source vertex and at least one destination vertex based on the target number and the recursive vector.

Patent Agency Ranking