利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

282 条记录 (耗时 0.027 秒)

    Machine learning model training method and apparatus
    2.
    发明授权
    Machine learning model training method and apparatus 有权

    公开(公告)号：US12067483B2

    公开(公告)日：2024-08-20

    申请号：US16431393

    申请日：2019-06-04

    申请人： HUAWEI TECHNOLOGIES CO., LTD.

    发明人： Bin Wu ,  Fengwei Zhou ,  Zhenguo Li

    IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06N99/00

    CPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06N99/00

    摘要： Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.

    METHOD AND APPARATUS FOR GENERATING QUANTUM ERROR CORRECTION CODE USING GRAPH STATE
    8.
    发明申请
    METHOD AND APPARATUS FOR GENERATING QUANTUM ERROR CORRECTION CODE USING GRAPH STATE 审中-公开

    公开(公告)号：US20190199373A1

    公开(公告)日：2019-06-27

    申请号：US16309281

    申请日：2016-06-24

    申请人： KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION

    发明人： Jun HEO ,  Il Kwon SOHN

    IPC分类号： H03M13/11 ,  H03M13/00 ,  G06N10/00

    CPC分类号： H03M13/1108 ,  G06N10/00 ,  G06N99/00 ,  H03M13/11 ,  H03M13/29 ,  H03M13/616

    摘要： Provided is a quantum error correction code generating method using a graph state. According to the exemplary embodiment of the present invention, a quantum error correction code generating method using a graph state: includes: generating a graph state representing an adjacency relationship between a plurality of qubits including at least one entangled qubit (ebit); generating a first stabilizer generator which corresponds to the graph state and is configured by a plurality of stabilizers for detecting errors of the plurality of qubits; and generating at least one logical Z operator used for a phase flip operation of a codeword, at least one logical X operator used for a bit flip operation of a codeword, and a second stabilizer generator which is a sub set of the first stabilizer generator, based on the first stabilizer generator and the at least one entangled qubit.

    LEARNING SERVICE PROVIDING APPARATUS
    10.
    发明申请
    LEARNING SERVICE PROVIDING APPARATUS 审中-公开

    公开(公告)号：US20180349757A1

    公开(公告)日：2018-12-06

    申请号：US16059100

    申请日：2018-08-09

    申请人： OMRON Corporation

    发明人： Tanichi ANDO

    IPC分类号： G06N3/04 ,  G06N3/08 ,  G06K9/62

    CPC分类号： G06N99/00

    摘要： A request acceptance unit accepts, as learning request information, information necessary for performing machine learning with respect to an ability to be added to a target apparatus, from a requester. A learning simulator performs machine learning according to the learning request information accepted from the requester. An ability providing data generation unit generates, based on a learning result obtained by the learning simulator, ability providing data, which is data for adding a new ability acquired as the learning result to the target apparatus. A service providing unit provides the ability providing data to the requester.