COMPACT NEURAL NETWORKS USING CONDENSED FILTERS

    公开(公告)号:US20210073613A1

    公开(公告)日:2021-03-11

    申请号:US16949994

    申请日:2020-11-23

    Applicant: Snap Inc.

    Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

    Compact neural networks using condensed filters

    公开(公告)号:US12136026B2

    公开(公告)日:2024-11-05

    申请号:US18222649

    申请日:2023-07-17

    Applicant: Snap Inc.

    Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

    COMPACT NEURAL NETWORKS USING CONDENSED FILTERS

    公开(公告)号:US20230359859A1

    公开(公告)日:2023-11-09

    申请号:US18222649

    申请日:2023-07-17

    Applicant: Snap Inc.

    CPC classification number: G06N3/04 G06T7/10 G06T5/20

    Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

    Compact neural networks using condensed filters

    公开(公告)号:US11763130B2

    公开(公告)日:2023-09-19

    申请号:US16949994

    申请日:2020-11-23

    Applicant: Snap Inc.

    CPC classification number: G06N3/04 G06T5/20 G06T7/10

    Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

Patent Agency Ranking