中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.023 seconds)

    EFFICIENT POSE ESTIMATION THROUGH ITERATIVE REFINEMENT
    2.
    发明申请
    EFFICIENT POSE ESTIMATION THROUGH ITERATIVE REFINEMENT 审中-公开

    公开(公告)号：WO2022198210A1

    公开(公告)日：2022-09-22

    申请号：PCT/US2022/071171

    申请日：2022-03-15

    Applicant: QUALCOMM INCORPORATED

    Inventor： YANG, John ,  BHALGAT, Yash Sanjay ,  PORIKLI, Fatih Murat ,  CHANG, Simyung

    IPC: G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06V40/10

    Abstract: Certain aspects of the present disclosure provide a method, including: processing input data with a feature extraction stage of a machine learning model to generate a feature map; applying an attention map to the feature map to generate an augmented feature map; processing the augmented feature map with a refinement stage of the machine learning model to generate a refined feature map; processing the refined feature map with a first regression stage of the machine learning model to generate multi-dimensional task output data; and processing the refined feature data with an attention stage of the machine learning model to generate an updated attention map.

    LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS
    3.
    发明申请
    LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS 审中-公开

    公开(公告)号：WO2021072338A1

    公开(公告)日：2021-04-15

    申请号：PCT/US2020/055167

    申请日：2020-10-10

    Applicant: QUALCOMM INCORPORATED

    Inventor： AZARIAN YAZDI, Kambiz ,  BLANKEVOORT, Tijmen Pieter Frederik ,  LEE, Jin Won ,  BHALGAT, Yash Sanjay

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

    Abstract: A method for pruning weights of an artificial neural network based on a learned threshold includes determining a pruning threshold for pruning a first set of pre-trained weights of multiple pre-trained weights based on a function of a classification loss and a regularization loss. The first set of pre-trained weights is pruned in response to a first value of each pre-trained weight in the first set of pre-trained weights being greater than the pruning threshold. A second set of pre-trained weights of the multiple pre-trained weights is fine-tuned or adjusted in response to a second value of each pre-trained weight in the second set of pre-trained weights being greater than the pruning threshold.

    CONVOLUTION WITH KERNEL EXPANSION AND TENSOR ACCUMULATION
    4.
    发明申请
    CONVOLUTION WITH KERNEL EXPANSION AND TENSOR ACCUMULATION 审中-公开

    公开(公告)号：WO2022256814A1

    公开(公告)日：2022-12-08

    申请号：PCT/US2022/072709

    申请日：2022-06-02

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  BHALGAT, Yash Sanjay ,  PARK, Edwin Chongwoo

    IPC: G06N3/04 ,  G06N3/063

    Abstract: Certain aspects of the present disclosure provide techniques for kernel expansion. An input data tensor is received at a first layer in a neural network, and a first convolution is performed for a first kernel, where the first kernel has a size greater than a preferred size. Performing the first convolution comprises generating a plurality of intermediate tensors by performing a plurality of intermediate convolutions using a plurality of intermediate kernels with a size of the preferred size, and accumulating the plurality of intermediate tensors to generate an output tensor for the first convolution.

Patent Agency Ranking