利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.019 秒)

    DYNAMIC NEURAL NETWORK MODEL SPARSIFICATION
    2.
    发明公开
    DYNAMIC NEURAL NETWORK MODEL SPARSIFICATION 审中-公开

    公开(公告)号：US20240119291A1

    公开(公告)日：2024-04-11

    申请号：US18203552

    申请日：2023-05-30

    申请人： NVIDIA Corporation

    发明人： Jose M. Alvarez Lopez ,  Pavlo Molchanov ,  Hongxu Yin ,  Maying Shen ,  Lei Mao ,  Xinglong Sun

    IPC分类号： G06N3/082 ,  G06N3/0495

    CPC分类号： G06N3/082 ,  G06N3/0495

    摘要： Machine learning is a process that learns a neural network model from a given dataset, where the model can then be used to make a prediction about new data. In order to reduce the size, computation, and latency of a neural network model, a compression technique can be employed which includes model sparsification. To avoid the negative consequences of pruning a fully pretrained neural network model and on the other hand of training a sparse model in the first place without any recovery option, the present disclosure provides a dynamic neural network model sparsification process which allows for recovery of previously pruned parts to improve the quality of the sparse neural network model.

    SHARPNESS-AWARE MINIMIZATION FOR ROBUSTNESS IN SPARSE NEURAL NETWORKS
    5.
    发明公开
    SHARPNESS-AWARE MINIMIZATION FOR ROBUSTNESS IN SPARSE NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240127067A1

    公开(公告)日：2024-04-18

    申请号：US18459083

    申请日：2023-08-31

    申请人： NVIDIA Corporation

    发明人： Annamarie Bair ,  Hongxu Yin ,  Pavlo Molchanov ,  Maying Shen ,  Jose Manuel Alvarez Lopez

    IPC分类号： G06N3/082

    CPC分类号： G06N3/082

    摘要： Systems and methods are disclosed for improving natural robustness of sparse neural networks. Pruning a dense neural network may improve inference speed and reduces the memory footprint and energy consumption of the resulting sparse neural network while maintaining a desired level of accuracy. In real-world scenarios in which sparse neural networks deployed in autonomous vehicles perform tasks such as object detection and classification for acquired inputs (images), the neural networks need to be robust to new environments, weather conditions, camera effects, etc. Applying sharpness-aware minimization (SAM) optimization during training of the sparse neural network improves performance for out of distribution (OOD) images compared with using conventional stochastic gradient descent (SGD) optimization. SAM optimizes a neural network to find a flat minimum: a region that both has a small loss value, but that also lies within a region of low loss.

    PRUNING A VISION TRANSFORMER
    7.
    发明申请
    PRUNING A VISION TRANSFORMER 有权

    公开(公告)号：US20230080247A1

    公开(公告)日：2023-03-16

    申请号：US17551005

    申请日：2021-12-14

    申请人： NVIDIA Corporation

    发明人： Hongxu Yin ,  Huanrui Yang ,  Pavlo Molchanov ,  Jan Kautz

    IPC分类号： G06V10/94 ,  G06V10/70

    摘要： A vision transformer is a deep learning model used to perform vision processing tasks such as image recognition. Vision transformers are currently designed with a plurality of same-size blocks that perform the vision processing tasks. However, some portions of these blocks are unnecessary and not only slow down the vision transformer but use more memory than required. In response, parameters of these blocks are analyzed to determine a score for each parameter, and if the score falls below a threshold, the parameter is removed from the associated block. This reduces a size of the resulting vision transformer, which reduces unnecessary memory usage and increases performance.

    LANDMARK DETECTION WITH AN ITERATIVE NEURAL NETWORK
    9.
    发明公开
    LANDMARK DETECTION WITH AN ITERATIVE NEURAL NETWORK 审中-公开

    公开(公告)号：US20240096115A1

    公开(公告)日：2024-03-21

    申请号：US18243555

    申请日：2023-09-07

    申请人： NVIDIA Corporation

    发明人： Pavlo Molchanov ,  Jan Kautz ,  Arash Vahdat ,  Hongxu Yin ,  Paul Micaelli

    IPC分类号： G06V20/59 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/16

    CPC分类号： G06V20/597 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/171 ,  G06T2207/30201 ,  G06V2201/07

    摘要： Landmark detection refers to the detection of landmarks within an image or a video, and is used in many computer vision tasks such emotion recognition, face identity verification, hand tracking, gesture recognition, and eye gaze tracking. Current landmark detection methods rely on a cascaded computation through cascaded networks or an ensemble of multiple models, which starts with an initial guess of the landmarks and iteratively produces corrected landmarks which match the input more finely. However, the iterations required by current methods typically increase the training memory cost linearly, and do not have an obvious stopping criteria. Moreover, these methods tend to exhibit jitter in landmark detection results for video. The present disclosure improves current landmark detection methods by providing landmark detection using an iterative neural network. Furthermore, when detecting landmarks in video, the present disclosure provides for a reduction in jitter due to reuse of previous hidden states from previous frames.