知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.016 seconds)

    Method and algorithm of recursive deep learning quantization for weight bit reduction
    1.
    发明授权
    Method and algorithm of recursive deep learning quantization for weight bit reduction 有权

    公开(公告)号：US11755908B2

    公开(公告)日：2023-09-12

    申请号：US17740344

    申请日：2022-05-09

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Zhengping Ji ,  John Wakefield Brothers

    IPC: G06N3/08 ,  G06N3/045 ,  G06N3/063

    CPC classification number: G06N3/08 ,  G06N3/045 ,  G06N3/063

    Abstract: A system and method to reduce weight storage bits for a deep-learning network includes a quantizing module and a cluster-number reduction module. The quantizing module quantizes neural weights of each quantization layer of the deep-learning network. The cluster-number reduction module reduces the predetermined number of clusters for a layer having a clustering error that is a minimum of the clustering errors of the plurality of quantization layers. The quantizing module requantizes the layer based on the reduced predetermined number of clusters for the layer and the cluster-number reduction module further determines another layer having a clustering error that is a minimum of the clustering errors of the plurality of quantized layers and reduces the predetermined number of clusters for the another layer until a recognition performance of the deep-learning network has been reduced by a predetermined threshold.

    Multiscale weighted matching and sensor fusion for dynamic vision sensor tracking
    5.
    发明授权
    Multiscale weighted matching and sensor fusion for dynamic vision sensor tracking 有权

    公开(公告)号：US10510160B2

    公开(公告)日：2019-12-17

    申请号：US15458016

    申请日：2017-03-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Zhengping Ji ,  Lilong Shi ,  Yibing Michelle Wang ,  Hyun Surk Ryu ,  Ilia Ovsiannikov

    IPC: G06K9/00 ,  G06T7/73

    Abstract: A Dynamic Vision Sensor (DVS) pose-estimation system includes a DVS, a transformation estimator, an inertial measurement unit (IMU) and a camera-pose estimator based on sensor fusion. The DVS detects DVS events and shapes frames based on a number of accumulated DVS events. The transformation estimator estimates a 3D transformation of the DVS camera based on an estimated depth and matches confidence-level values within a camera-projection model such that at least one of a plurality of DVS events detected during a first frame corresponds to a DVS event detected during a second subsequent frame. The IMU detects inertial movements of the DVS with respect to world coordinates between the first and second frames. The camera-pose estimator combines information from a change in a pose of the camera-projection model between the first frame and the second frame based on the estimated transformation and the detected inertial movements of the DVS.

    Apparatus and method for generating efficient convolution
    6.
    发明授权
    Apparatus and method for generating efficient convolution 有权

    公开(公告)号：US10997272B2

    公开(公告)日：2021-05-04

    申请号：US16460564

    申请日：2019-07-02

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Weiran Deng ,  Zhengping Ji

    IPC: G06F30/398 ,  G06F7/544 ,  G06F7/556 ,  G06N3/04 ,  G06N3/063 ,  G06F17/15

    Abstract: A method of manufacturing an apparatus and a method of constructing an integrated circuit are provided. The method of manufacturing an apparatus includes forming the apparatus on a wafer or a package with at least one other apparatus, wherein the apparatus comprises a polynomial generator, a first matrix generator, a second matrix generator, a third matrix generator, and a convolution generator; and testing the apparatus, wherein testing the apparatus comprises testing the apparatus using one or more electrical to optical converters, one or more optical splitters that split an optical signal into two or more optical signals, and one or more optical to electrical converters.

    Multiscale weighted matching and sensor fusion for dynamic vision sensor tracking
    7.
    发明授权
    Multiscale weighted matching and sensor fusion for dynamic vision sensor tracking 有权

    公开(公告)号：US10733760B2

    公开(公告)日：2020-08-04

    申请号：US16597846

    申请日：2019-10-09

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Zhengping Ji ,  Lilong Shi ,  Yibing Michelle Wang ,  Hyun Surk Ryu ,  Ilia Ovsiannikov

    IPC: G06K9/00 ,  G06T7/73

    Abstract: A Dynamic Vision Sensor (DVS) pose-estimation system includes a DVS, a transformation estimator, an inertial measurement unit (IMU) and a camera-pose estimator based on sensor fusion. The DVS detects DVS events and shapes frames based on a number of accumulated DVS events. The transformation estimator estimates a 3D transformation of the DVS camera based on an estimated depth and matches confidence-level values within a camera-projection model such that at least one of a plurality of DVS events detected during a first frame corresponds to a DVS event detected during a second subsequent frame. The IMU detects inertial movements of the DVS with respect to world coordinates between the first and second frames. The camera-pose estimator combines information from a change in a pose of the camera-projection model between the first frame and the second frame based on the estimated transformation and the detected inertial movements of the DVS.

Patent Agency Ranking