中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

48 records (took 0.017 seconds)

    METHOD AND APPARATUS FOR VIDEO SUPER RESOLUTION USING CONVOLUTIONAL NEURAL NETWORK WITH TWO-STAGE MOTION COMPENSATION
    21.
    发明申请
    METHOD AND APPARATUS FOR VIDEO SUPER RESOLUTION USING CONVOLUTIONAL NEURAL NETWORK WITH TWO-STAGE MOTION COMPENSATION 审中-公开

    公开(公告)号：US20200294217A1

    公开(公告)日：2020-09-17

    申请号：US16887511

    申请日：2020-05-29

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa EL-KHAMY ,  Haoyu REN ,  Jungwon LEE

    IPC: G06T5/50 ,  G06T3/00 ,  G06K9/62 ,  G06K9/68 ,  G06T3/40

    Abstract: A method and an apparatus are provided. The method includes receiving a video with a first plurality of frames having a first resolution; generating a plurality of warped frames from the first plurality of frames based on a first type of motion compensation; generating a second plurality of frames having a second resolution, wherein the second resolution is of higher resolution than the first resolution, wherein each of the second plurality of frames having the second resolution is derived from a subset of the plurality of warped frames using a convolutional network; and generating a third plurality of frames having the second resolution based on a second type of motion compensation, wherein each of the third plurality of frames having the second resolution is derived from a fusing a subset of the second plurality of frames.

    APPARATUS AND METHOD FOR STUDENT-TEACHER TRANSFER LEARNING NETWORK USING KNOWLEDGE BRIDGE
    22.
    发明申请
    APPARATUS AND METHOD FOR STUDENT-TEACHER TRANSFER LEARNING NETWORK USING KNOWLEDGE BRIDGE 审中-公开

    公开(公告)号：US20180336465A1

    公开(公告)日：2018-11-22

    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

    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
    25.
    发明申请
    SYSTEM AND METHODS FOR LOW COMPLEXITY LIST DECODING OF TURBO CODES AND CONVOLUTIONAL CODES 审中-公开
    系统和方法用于低复杂度列表解码的涡轮代码和转换代码

    公开(公告)号：US20150236717A1

    公开(公告)日：2015-08-20

    申请号：US14565082

    申请日：2014-12-09

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa EL-KHAMY ,  Jinhong WU ,  Jungwon LEE ,  Inyup KANG

    IPC: H03M13/09 ,  H03M13/00

    CPC classification number: H03M13/3905 ,  G06F11/1004 ,  G11B2020/1843 ,  H03M13/3738 ,  H03M13/3922 ,  H03M13/3972 ,  H03M13/451

    Abstract: A method and system for decoding a signal are provided. The method includes receiving a signal, where the signal includes at least one symbol; decoding the signal in stages, where each at least one symbol is decoded into at least one bit per stage, wherein a Log-Likelihood Ratio (LLR) and a path metric are determined for each possible path for each at least one bit at each stage; determining the magnitudes of the LLRs; identifying K bits of the signal with the smallest corresponding LLR magnitudes; identifying, for each of the K bits, L possible paths with the 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.

    Abstract translation: 提供了一种用于解码信号的方法和系统。 该方法包括接收信号，其中该信号包括至少一个符号; 其中每个至少一个符号被解码成每级至少一个比特，其中为每个阶段的每个至少一个比特确定每个可能路径的对数似然比（LLR）和路径量度 ; 确定LLR的大小; 识别具有最小对应LLR幅度的信号的K位; 针对用户可定义数量的解码器级，为每个解码器级识别具有最大路径度量的L个可能路径中的每一个的K个比特; 对于L个可能路径中的每一个，执行前向和后向跟踪，以确定候选码字; 对候选码字执行循环冗余校验（CRC），并在第一候选码字通过CRC之后停止。

    SYSTEMS AND METHODS FOR NEURAL ARCHITECTURE SEARCH
    27.
    发明公开
    SYSTEMS AND METHODS FOR NEURAL ARCHITECTURE SEARCH 审中-公开

    公开(公告)号：US20240070455A1

    公开(公告)日：2024-02-29

    申请号：US18148418

    申请日：2022-12-29

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Mostafa EL-KHAMY ,  Yanlin ZHOU

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: A system and a method are disclosed for neural architecture search. In some embodiments, the method includes: processing a training data set with a neural network during a first epoch of training of the neural network; computing a training loss using a smooth maximum unit regularization value; and adjusting a plurality of multiplicative connection weights and a plurality of parametric connection weights of the neural network in a direction that reduces the training loss.

Patent Agency Ranking