知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

319 records (took 0.037 seconds)

    METHOD AND APPARATUS FOR FEDERATED LEARNING
    84.
    发明申请
    METHOD AND APPARATUS FOR FEDERATED LEARNING 有权

    公开(公告)号：US20220058507A1

    公开(公告)日：2022-02-24

    申请号：US17179964

    申请日：2021-02-19

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa El-Khamy ,  Weituo Hao ,  Jungwon Lee

    IPC: G06N7/00 ,  G06N20/00 ,  H04L29/08

    Abstract: Methods and devices are provided for performing federated learning. A global model is distributed from a server to a plurality of client devices. At each of the plurality of client devices: model inversion is performed on the global model to generate synthetic data; the global model is on an augmented dataset of collected data and the synthetic data to generate a respective client model; and the respective client model is transmitted to the server. At the server: client models are received from the plurality of client devices, where each client model is received from a respective client device of the plurality of client devices: model inversion is performed on each client model to generate a synthetic dataset; the client models are averaged to generate an averaged model; and the averaged model is trained using the synthetic dataset to generate an updated model.

    Apparatus and method for student-teacher transfer learning network using knowledge bridge
    85.
    发明授权
    Apparatus and method for student-teacher transfer learning network using knowledge bridge 有权

    公开(公告)号：US11195093B2

    公开(公告)日：2021-12-07

    申请号：US15867303

    申请日：2018-01-10

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Jaeyoung Kim ,  Mostafa El-Khamy ,  Jungwon Lee

    IPC: G06N3/08 ,  G06N7/00 ,  G06N3/04

    Abstract: An apparatus, a method, a method of manufacturing and apparatus, and a method of constructing an integrated circuit are provided. The apparatus includes a teacher network; a student network; a plurality of knowledge bridges between the teacher network and the student network, where each of the plurality of knowledge bridges provides a hint about a function being learned, and where a hint includes a mean square error or a probability; and a loss function device connected to the plurality of knowledge bridges and the student network. The method includes training a teacher network; providing hints to a student network by a plurality of knowledge bridges between the teacher network and the student network; and determining a loss function from outputs of the plurality of knowledge bridges and the student network.

    System and methods for low complexity list decoding of turbo codes and convolutional codes
    87.
    发明授权
    System and methods for low complexity list decoding of turbo codes and convolutional codes 有权

    公开(公告)号：US11043976B2

    公开(公告)日：2021-06-22

    申请号：US16272653

    申请日：2019-02-11

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa El-Khamy ,  Jinhong Wu ,  Jungwon Lee ,  Inyup Kang

    IPC: H03M13/00 ,  H03M13/39 ,  G06F11/10 ,  G11B20/18 ,  H03M13/37 ,  H03M13/45

    Abstract: A method, system, and non-transitory computer-readable recording medium of decoding a signal are provided. The method includes receiving signal to be decoded, where signal includes at least one symbol; decoding signal in stages, where each at least one symbol of signal is decoded into at least one bit per stage, wherein Log-Likelihood Ratio (LLR) and a path metric are determined for each possible path for each at least one bit at each stage; determining magnitudes of the LLRs; identifying K bits of the signal with smallest corresponding LLR magnitudes; identifying, for each of the K bits, L possible paths with largest path metrics at each decoder stage for a user-definable number of decoder stages; performing forward and backward traces, for each of the L possible paths, to determine candidate codewords; performing a Cyclic Redundancy Check (CRC) on the candidate codewords; and stopping after a first candidate codeword passes the CRC.

    System and methods for low complexity list decoding of turbo codes and convolutional codes
    90.
    发明授权
    System and methods for low complexity list decoding of turbo codes and convolutional codes 有权

    公开(公告)号：US10938420B2

    公开(公告)日：2021-03-02

    申请号：US16272722

    申请日：2019-02-11

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa El-Khamy ,  Jinhong Wu ,  Jungwon Lee ,  Inyup Kang

    IPC: H03M13/00 ,  H03M13/39 ,  G06F11/10 ,  G11B20/18 ,  H03M13/37 ,  H03M13/45

    Abstract: Method for decoding signal includes receiving signal, where signal includes at least one symbol; decoding signal in stages, where each at least one symbol of signal is decoded into at least one bit per stage, wherein Log-Likelihood Ratio (LLR) for each at least one bit at each stage is determined, and identified in vector LAPP; performing Cyclic Redundancy Check (CRC) on LAPP, and stopping if LAPP passes CRC; otherwise, determining magnitudes of LLRs in LAPP; identifying K LLRs in LAPP with smallest magnitudes and indexing K LLRs as r={r(1), r(2), . . . , r(K)}; setting Lmax to maximum magnitude of LLRs in LAPP or maximum possible LLR quantization value; setting v=1; generating {tilde over (L)}A(r(k))=LA(r(k))−Lmaxvksign[LAPP(r(k))], for k=1, 2, . . . , K; decoding with {tilde over (L)}A to identify {tilde over (L)}APP, wherein {tilde over (L)}APP is LLR vector; and performing CRC on {tilde over (L)}APP, and stopping if {tilde over (L)}APP passes CRC or v=2K-1; otherwise, incrementing v and returning to generating {tilde over (L)}A(r(k)).

Patent Agency Ranking