利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

4 条记录 (耗时 0.012 秒)

    A NEURAL NETWORK WITH A LAYER SOLVING A SEMIDEFINITE PROGRAM
    1.
    发明公开
    A NEURAL NETWORK WITH A LAYER SOLVING A SEMIDEFINITE PROGRAM 审中-公开

    公开(公告)号：EP3742345A1

    公开(公告)日：2020-11-25

    申请号：EP19176011.5

    申请日：2019-05-22

    申请人： Robert Bosch GmbH ,  Carnegie Mellon University

    发明人： Kolter, Jeremy Zieg ,  Domokos, Csaba ,  Wang, Po-Wei ,  Donti, Priya Lekha

    IPC分类号： G06N3/04 ,  G06N3/08 ,  G06N5/00

    摘要： A system (100) is disclosed for applying a neural network to an input instance. The neural network comprises an optimization layer for determining values of one or more output neurons from values of one or more input neurons by a joint optimization parametrized by one or more parameters. An input instance is obtained. The values of the one or more input neurons to the optimization layer are obtained and input vectors for the one or more input neurons are determined therefrom. Output vectors for the one or more output neurons are computed from the determined input vectors by jointly optimizing at least the output vectors with respect to the input vectors to solve a semidefinite program defined by the one or more parameters. The values of the one or more output neurons are determined from the respective computed output vectors.

    METHOD AND SYSTEM FOR LEARNING RULES FROM A DATA BASE
    2.
    发明公开
    METHOD AND SYSTEM FOR LEARNING RULES FROM A DATA BASE 审中-公开

    公开(公告)号：EP3798862A1

    公开(公告)日：2021-03-31

    申请号：EP19199308.8

    申请日：2019-09-24

    申请人： Robert Bosch GmbH ,  Carnegie Mellon University

    发明人： Domokos, Csaba ,  Stepanova, Daria ,  Wang, Po-wei ,  Kolter, Jeremy Zieg

    IPC分类号： G06F16/25 ,  G06F16/28 ,  G06N3/00 ,  G06N20/00

    摘要： System (300) and computer implemented method (200) for learning rules from a data base (100) comprising entities (110) and relations (120) between said entities, wherein an entity (110) is either a constant (C1, C2, C3, C4, C5, C6, C7) or a numerical value (N1, N2, N3), and a relation (120) between a constant (C6, C7) and a numerical value (N1, N2, N3) is a numerical relation (120b) and a relation (120) between two constants (C1, C2, C3, C4) is a non-numerical relation (120a), the method (200) comprising steps of:
    deriving (210) aggregate values from said numerical and/or non-numerical relations;
    deriving (220) non-numerical relations from said aggregate values;
    adding (230) said derived non-numerical relations to the data base;
    constructing (240) differentiable operators, wherein a differentiable operator refers to a non-numerical or a derived non-numerical relation of the data base, and extracting (250) rules from said differentiable operators.

    A DEVICE, A COMPUTER PROGRAM AND A COMPUTER-IMPLEMENTED METHOD FOR TRAINING A KNOWLEDGE GRAPH EMBEDDING MODEL
    3.
    发明公开
    A DEVICE, A COMPUTER PROGRAM AND A COMPUTER-IMPLEMENTED METHOD FOR TRAINING A KNOWLEDGE GRAPH EMBEDDING MODEL 审中-公开

    公开(公告)号：EP4109348A1

    公开(公告)日：2022-12-28

    申请号：EP21181822.4

    申请日：2021-06-25

    申请人： Robert Bosch GmbH

    发明人： Domokos, Csaba ,  Stepanova, Daria ,  Andresel, Medina ,  Tran, Trung Kien

    IPC分类号： G06N3/08 ,  G06N5/02 ,  G06N5/04

    摘要： Device, computer program, computer-implemented method for training a knowledge graph embedding model (208) of a knowledge graph (200) that is enhanced by an ontology (202), wherein the method comprises training (2) the knowledge graph embedding model (208) with a first training query and its predetermined answer to reduce, in particular minimize, a distance between an embedding of the answer in the knowledge graph embedding model (208) and an embedding of the first training query in knowledge graph embedding model (208), and to reduce, in particular minimize, a distance between the embedding of the answer and an embedding of a second training query in knowledge graph embedding model (208), wherein the second training query is determined (1) from the first training query depending on the ontology (202).