中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.023 seconds)

    DEPTH-FIRST DEEP CONVOLUTIONAL NEURAL NETWORK INFERENCE
    1.
    发明申请
    DEPTH-FIRST DEEP CONVOLUTIONAL NEURAL NETWORK INFERENCE 有权

    公开(公告)号：US20210182684A1

    公开(公告)日：2021-06-17

    申请号：US17121499

    申请日：2020-12-14

    Applicant: QUALCOMM Incorporated

    Inventor： Piero ZAPPI ,  Jin Won LEE ,  Christopher LOTT ,  Rexford Alan HILL

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A method performed by a computing device includes determining a partition for depth-first processing by a multi-layer artificial neural network (ANN) of the computing device. The computing device comprising a processor, on-chip memory, and off-chip memory. The first partition determined based on an amount of on-chip memory used by the first partition, an available amount of on-chip memory, and a size of a write back to the off-chip memory. The method also includes processing, at the device via the multi-layer ANN, an input, using the depth-first processing in accordance with the partition.

    EFFICIENT INFERENCING WITH PIECEWISE POINTWISE CONVOLUTION
    2.
    发明申请
    EFFICIENT INFERENCING WITH PIECEWISE POINTWISE CONVOLUTION 有权

    公开(公告)号：US20210019593A1

    公开(公告)日：2021-01-21

    申请号：US16932496

    申请日：2020-07-17

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Jin Won LEE ,  Jilei HOU

    IPC: G06N3/04 ,  G06F11/30 ,  G06K9/62 ,  G06F17/15

    Abstract: Certain aspects of the present disclosure provide techniques for performing piecewise pointwise convolution, comprising: performing a first piecewise pointwise convolution on a first subset of data received via a first branch input at a piecewise pointwise convolution layer of a convolutional neural network (CNN) model; performing a second piecewise pointwise convolution on a second subset of data received via a second branch input at the piecewise pointwise convolution layer; determining a piecewise pointwise convolution output by summing a result of the first piecewise pointwise convolution and a result of the second piecewise pointwise convolution; and providing the piecewise pointwise convolution output to a second layer of the CNN model.

    POWER STATE CONTROL OF A MOBILE DEVICE
    4.
    发明申请
    POWER STATE CONTROL OF A MOBILE DEVICE 审中-公开

    公开(公告)号：US20190094941A1

    公开(公告)日：2019-03-28

    申请号：US15713254

    申请日：2017-09-22

    Applicant: QUALCOMM Incorporated

    Inventor： Shankar SADASIVAM ,  Jin Won LEE

    IPC: G06F1/32 ,  G06F9/50

    Abstract: A method of operating a shared resource in a mobile device includes extracting a set of features from a plurality of subsystems of the mobile device. The set of features may be extracted from each subsystem of the plurality of subsystems requesting services from one or more shared resources of the mobile device. One or more parameter of the shared resource(s) may be determined based on the extracted set of features from the plurality of subsystems. The shared resource(s) may be operated based on the determined parameter(s).

    LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS
    6.
    发明申请
    LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS 有权

    公开(公告)号：US20210110268A1

    公开(公告)日：2021-04-15

    申请号：US17067233

    申请日：2020-10-09

    Applicant: QUALCOMM Incorporated

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

    IPC: G06N3/08 ,  G06N3/04

    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 pretrained 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.

    METHODS AND APPARATUSES FOR DETECTING MOTION DISORDER SYMPTOMS BASED ON SENSOR DATA
    7.
    发明申请
    METHODS AND APPARATUSES FOR DETECTING MOTION DISORDER SYMPTOMS BASED ON SENSOR DATA 审中-公开
    用于检测基于传感器数据的运动障碍症状的方法和装置

    公开(公告)号：US20170049376A1

    公开(公告)日：2017-02-23

    申请号：US15237851

    申请日：2016-08-16

    Applicant: QUALCOMM Incorporated

    Inventor： Jin Won LEE ,  Xinzhou WU ,  Parixit Laljibhai AGHERA ,  Rashid Ahmed Akbar ATTAR

    IPC: A61B5/00 ,  A61B5/11

    CPC classification number: A61B5/4082 ,  A61B5/0022 ,  A61B5/1118 ,  A61B5/1123 ,  A61B5/6824 ,  A61B5/6829 ,  A61B5/6898 ,  A61B5/7264 ,  A61B5/7275 ,  A61B5/7278 ,  A61B5/742 ,  A61B2562/0204 ,  A61B2562/0219 ,  A61B2562/0223 ,  G16H40/63 ,  G16H50/20 ,  G16H50/30

    Abstract: Disclosed are techniques for determining a severity of motion disorder symptoms by receiving sensor data from one or more sensors, determining that the sensor data represents one or more activities of daily life (ADLs) of a user, assigning one or more probabilities to the one or more determined ADLs, each probability of the one or more probabilities indicating a confidence level that the sensor data represents a corresponding ADL, and providing the sensor data and the one or more probabilities to a motion disorder symptom scoring module that generates one or more scores for the one or more determined ADLs based on the sensor data, each score of the one or more scores indicating the severity of the motion disorder symptoms for a corresponding ADL, and combines the one or more scores and the one or more probabilities to generate an aggregated severity score for the motion disorder symptoms.

    Abstract translation: 公开了通过从一个或多个传感器接收传感器数据来确定运动障碍症状的严重性的技术，确定传感器数据表示用户的一个或多个日常生活活动（ADL），将一个或多个概率分配给一个或多个 更确定的ADL，所述一个或多个概率的每个概率指示所述传感器数据表示对应的ADL的置信水平，以及将所述传感器数据和所述一个或多个概率提供给运动障碍症状评分模块，所述运动障碍症状评分模块为 所述一个或多个确定的ADL基于所述传感器数据，所述一个或多个评分的每个评分指示相应ADL的运动障碍症状的严重性，并且组合所述一个或多个分数与所述一个或多个概率以生成聚合 运动障碍症状严重程度评分。

    PLACE OF RELEVANCE DETERMINATION IN A CELLULAR NETWORK
    9.
    发明申请
    PLACE OF RELEVANCE DETERMINATION IN A CELLULAR NETWORK 审中-公开
    细胞网络中相关性测定的位置

    公开(公告)号：US20160037291A1

    公开(公告)日：2016-02-04

    申请号：US14450856

    申请日：2014-08-04

    Applicant: QUALCOMM Incorporated

    Inventor： Shankar SADASIVAM ,  Jin Won LEE

    IPC: H04W4/02

    CPC classification number: H04W64/00 ,  H04W84/042

    Abstract: A method includes receiving cellular network signals at a mobile device from several cells of a cellular network. The method then includes generating a place model representative of a characteristic of the place where the mobile device is located in response to the received cellular network signals. In one aspect, the place model is clustered with one or more previously generated place models if the place model is similar to the one or more previously generated place models. In another aspect, it is determined whether the place where the mobile device is located is a place of relevance to a user based on the clustering of one or more previously generated place models if the place model is similar to the one or more previously generated place models.

    Abstract translation: 一种方法包括从蜂窝网络的几个小区在移动设备处接收蜂窝网络信号。 该方法然后包括响应于接收到的蜂窝网络信号而生成代表移动设备所在位置的特征的地点模型。 在一个方面，如果地点模型类似于一个或多个先前生成的地点模型，则场所模型与一个或多个先前生成的地点模型聚类。 在另一方面，如果地点模型类似于一个或多个先前生成的地点，则基于一个或多个先前生成的地点模型的聚类，确定移动设备所在的地点是否是与用户相关的地方 楷模。

Patent Agency Ranking