中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.023 seconds)

    Training neural networks for vehicle re-identification
    21.
    发明授权
    Training neural networks for vehicle re-identification 有权

    公开(公告)号：US12154188B2

    公开(公告)日：2024-11-26

    申请号：US17890849

    申请日：2022-08-18

    Applicant: NVIDIA Corporation

    Inventor： Fnu Ratnesh Kumar ,  Farzin Aghdasi ,  Parthasarathy Sriram ,  Edwin Weill

    IPC: G06T1/20 ,  G06F17/18 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V20/58

    Abstract: In various examples, a neural network may be trained for use in vehicle re-identification tasks—e.g., matching appearances and classifications of vehicles across frames—in a camera network. The neural network may be trained to learn an embedding space such that embeddings corresponding to vehicles of the same identify are projected closer to one another within the embedding space, as compared to vehicles representing different identities. To accurately and efficiently learn the embedding space, the neural network may be trained using a contrastive loss function or a triplet loss function. In addition, to further improve accuracy and efficiency, a sampling technique—referred to herein as batch sample—may be used to identify embeddings, during training, that are most meaningful for updating parameters of the neural network.

    MULTI-TRACK MACHINE LEARNING MODEL TRAINING USING EARLY TERMINATION IN CLOUD-SUPPORTED PLATFORMS
    26.
    发明公开
    MULTI-TRACK MACHINE LEARNING MODEL TRAINING USING EARLY TERMINATION IN CLOUD-SUPPORTED PLATFORMS 审中-公开

    公开(公告)号：US20230342666A1

    公开(公告)日：2023-10-26

    申请号：US18139016

    申请日：2023-04-25

    Applicant: NVIDIA Corporation

    Inventor： Steve Masson ,  Farzin Aghdasi ,  Parthasarathy Sriram ,  Arvind Sai Kumar ,  Varun Praveen

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Devices, systems, and techniques for experiment-based training of machine learning models (MLMs) using early stopping. The techniques include starting training tracks (TTs) that train candidate MLMs using the same training data and respective sets of training settings, performing a first evaluation of a first candidate MLM prior to completion of a corresponding first TT, and responsive to the first evaluation, placing the first TT on an inactive status, inactive status indicating that further training of the first candidate MLM is to be ceased. The techniques further include continuing at least a second TT using the training data, and responsive to conclusion of the TTs, selecting, as one or more final MLMs, the first candidate MLM or a second candidate MLM.

    PRUNING COMPLEX DEEP LEARNING MODELS BASED ON PARENT PRUNING INFORMATION
    28.
    发明公开
    PRUNING COMPLEX DEEP LEARNING MODELS BASED ON PARENT PRUNING INFORMATION 审中-公开

    公开(公告)号：US20230153612A1

    公开(公告)日：2023-05-18

    申请号：US18056559

    申请日：2022-11-17

    Applicant: NVIDIA Corporation

    Inventor： Yu Wang ,  Farzin Aghdasi ,  Parthasarathy Sriram

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: When visiting a child node in a graph corresponding to a deep learning model to analyze the child node for pruning in the deep learning model, data identifying pruning information corresponding to one or more parent nodes may be determined and used to access the pruning information. For example, a list of parent nodes of the parent node may be used to access the pruning information for the visit to the child node. The graph may be explored using recursion to iteratively visit nodes to determine portions of pruning information for pruning a node where a portion of the pruning information determined for prior visits to the nodes may be reused. A layer of the deep learning model including multiple dependent convolutions may be pruned by treating each convolution as a separate node and/or layer.

    PRUNING NEURAL NETWORKS THAT INCLUDE ELEMENT-WISE OPERATIONS
    30.
    发明申请
    PRUNING NEURAL NETWORKS THAT INCLUDE ELEMENT-WISE OPERATIONS 审中-公开

    公开(公告)号：US20200160185A1

    公开(公告)日：2020-05-21

    申请号：US16197986

    申请日：2018-11-21

    Applicant: NVIDIA CORPORATION

    Inventor： Varun Praveen ,  Anil Ubale ,  Parthasarathy Sriram ,  Greg Heinrich ,  Tayfun Gurel

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Input layers of an element-wise operation in a neural network can be pruned such that the shape (e.g., the height, the width, and the depth) of the pruned layers matches. A pruning engine identifies all of the input layers into the element-wise operation. For each set of corresponding neurons in the input layers, the pruning engine equalizes the metrics associated with the neurons to generate an equalized metric associated with the set. The pruning engine prunes the input layers based on the equalized metrics generated for each unique set of corresponding neurons.

Patent Agency Ranking