知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.014 seconds)

    RADAR BASED USER INTERFACE
    2.
    发明申请
    RADAR BASED USER INTERFACE 审中-公开
    基于雷达的用户界面

    公开(公告)号：US20160259037A1

    公开(公告)日：2016-09-08

    申请号：US15060545

    申请日：2016-03-03

    Applicant: NVIDIA Corporation

    Inventor： Pavlo MOLCHANOV ,  Shalini GUPTA ,  Kihwan KIM ,  Kari PULLI

    IPC: G01S7/41 ,  G01S13/56 ,  G01S7/35 ,  G01S13/42

    CPC classification number: G06F3/017 ,  B60R11/04 ,  G01S7/352 ,  G01S7/415 ,  G01S13/42 ,  G01S13/584 ,  G06F3/011 ,  G06K9/00355 ,  G06K9/6256 ,  G06K9/6267 ,  G06K9/6288 ,  G06K9/78 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/082 ,  G06N3/084

    Abstract: An apparatus and method for radar based gesture detection. The apparatus includes a processing element and a transmitter configured to transmit radar signals. The transmitter is coupled to the processing element. The apparatus further includes a plurality of receivers configured to receive radar signal reflections, where the plurality of receivers is coupled to the processing element. The transmitter and plurality of receivers are configured for short range radar and the processing element is configured to detect a hand gesture based on the radar signal reflections received by the plurality of receivers.

    Abstract translation: 一种用于基于雷达的手势检测的装置和方法。 该装置包括处理元件和被配置为发射雷达信号的发射机。 发射器耦合到处理元件。 该装置还包括被配置为接收雷达信号反射的多个接收器，其中多个接收器耦合到处理元件。 发射器和多个接收器被配置用于短距离雷达，并且处理元件被配置为基于由多个接收器接收的雷达信号反射来检测手势。

    TECHNIQUES FOR TRAINING VISION FOUNDATION MODELS VIA MULTI-TEACHER DISTILLATION
    3.
    发明申请
    TECHNIQUES FOR TRAINING VISION FOUNDATION MODELS VIA MULTI-TEACHER DISTILLATION 有权

    公开(公告)号：US20250165777A1

    公开(公告)日：2025-05-22

    申请号：US18740294

    申请日：2024-06-11

    Applicant: NVIDIA CORPORATION

    Inventor： Michael RANZINGER ,  Gregory HEINRICH ,  Jan KAUTZ ,  Pavlo MOLCHANOV

    IPC: G06N3/08 ,  G06N3/045

    Abstract: One embodiment of a method for training a first machine learning model includes processing first data via a plurality of trained machine learning models to generate a plurality of first outputs, processing the first data via the first machine learning model to generate a second output, processing the second output via a plurality of projection heads to generate a plurality of third outputs, computing a plurality of losses based on the plurality of first outputs and the plurality of third outputs, and performing one or more operations to update one or more parameters of the first machine learning model and one or more parameters of the plurality of projection heads based on the plurality of losses.

    ADAPTIVE TOKEN DEPTH ADJUSTMENT IN TRANSFORMER NEURAL NETWORKS
    4.
    发明公开
    ADAPTIVE TOKEN DEPTH ADJUSTMENT IN TRANSFORMER NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230186077A1

    公开(公告)日：2023-06-15

    申请号：US17841577

    申请日：2022-06-15

    Applicant: NVIDIA CORPORATION

    Inventor： Hongxu YIN ,  Jan KAUTZ ,  Jose Manuel ALVAREZ LOPEZ ,  Arun MALLYA ,  Pavlo MOLCHANOV ,  Arash VAHDAT

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06N3/0481

    Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes computing a first set of halting scores for a first set of tokens that has been input into a first layer of the transformer neural network. The technique also includes determining that a first halting score included in the first set of halting scores exceeds a threshold value. The technique further includes in response to the first halting score exceeding the threshold value, causing a first token that is included in the first set of tokens and is associated with the first halting score not to be processed by one or more layers within the transformer neural network that are subsequent to the first layer.

Patent Agency Ranking