知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

48 records (took 0.017 seconds)

    EFFICIENT NEURAL NETWORKS WITH ELABORATE MATRIX STRUCTURES IN MACHINE LEARNING ENVIRONMENTS
    11.
    发明申请
    EFFICIENT NEURAL NETWORKS WITH ELABORATE MATRIX STRUCTURES IN MACHINE LEARNING ENVIRONMENTS 有权

    公开(公告)号：US20250053814A1

    公开(公告)日：2025-02-13

    申请号：US18805370

    申请日：2024-08-14

    Applicant: Intel Corporation

    Inventor： Yurong Chen ,  Jianguo Li ,  Renkun Ni

    IPC: G06N3/082 ,  G06N3/063 ,  G06N7/04

    Abstract: A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method of embodiments, as described herein, includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.

    Techniques for dense video descriptions
    12.
    发明授权
    Techniques for dense video descriptions 有权

    公开(公告)号：US11263489B2

    公开(公告)日：2022-03-01

    申请号：US16616533

    申请日：2017-06-29

    Applicant: INTEL CORPORATION

    Inventor： Yurong Chen ,  Jianguo Li ,  Zhou Su ,  Zhiqiang Shen

    IPC: G06K9/00 ,  G06K9/62 ,  G06F40/169 ,  G06N3/08

    Abstract: Techniques and apparatus for generating dense natural language descriptions for video content are described. In one embodiment, for example, an apparatus may include at least one memory and logic, at least a portion of the logic comprised in hardware coupled to the at least one memory, the logic to receive a source video comprising a plurality of frames, determine a plurality of regions for each of the plurality of frames, generate at least one region-sequence connecting the determined plurality of regions, apply a language model to the at least one region-sequence to generate description information comprising a description of at least a portion of content of the source video. Other embodiments are described and claimed.

    Efficient neural networks with elaborate matrix structures in machine learning environments
    17.
    发明授权
    Efficient neural networks with elaborate matrix structures in machine learning environments 有权

    公开(公告)号：US12165065B2

    公开(公告)日：2024-12-10

    申请号：US16632145

    申请日：2017-08-18

    Applicant: Intel Corporation

    Inventor： Yurong Chen ,  Jianguo Li ,  Renkun Ni

    IPC: G06N3/082 ,  G06N3/063 ,  G06N7/04

    Abstract: A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.

    Composite binary decomposition network
    18.
    发明授权
    Composite binary decomposition network 有权

    公开(公告)号：US11934949B2

    公开(公告)日：2024-03-19

    申请号：US16973608

    申请日：2018-09-27

    Applicant: Intel Corporation

    Inventor： Jianguo Li ,  Yurong Chen ,  Zheng Wang

    IPC: G06N3/08 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/084

    CPC classification number: G06N3/08 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/084

    Abstract: Embodiments are directed to a composite binary decomposition network. An embodiment of a computer-readable storage medium includes executable computer program instructions for transforming a pre-trained first neural network into a binary neural network by processing layers of the first neural network in a composite binary decomposition process, where the first neural network having floating point values representing weights of various layers of the first neural network. The composite binary decomposition process includes a composite operation to expand real matrices or tensors into a plurality of binary matrices or tensors, and a decompose operation to decompose one or more binary matrices or tensors of the plurality of binary matrices or tensors into multiple lower rank binary matrices or tensors.

Patent Agency Ranking