中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.016 seconds)

    METHOD AND APPARATUS WITH NEURAL NETWORK LAYER CONTRACTION
    1.
    发明申请
    METHOD AND APPARATUS WITH NEURAL NETWORK LAYER CONTRACTION 审中-公开

    公开(公告)号：US20200226451A1

    公开(公告)日：2020-07-16

    申请号：US16739543

    申请日：2020-01-10

    Applicant: Samsung Electronics Co., Ltd. ,  University of Zurich

    Inventor： Shih-Chii LIU ,  Bodo RUECKAUER ,  Tobi DELBRUCK

    IPC: G06N3/063 ,  G06N3/08 ,  G06N5/04

    Abstract: A processor-implemented neural network method includes: determining a reference sample among sequential input samples to be processed by a neural network, the neural network comprising an input layer, one or more hidden layers, and an output layer; performing an inference process of obtaining an output activation of the output layer based on operations in the hidden layers corresponding to the reference sample input to the input layer; determining layer contraction parameters for determining an affine transformation relationship between the input layer and the output layer, for approximation of the inference process; and performing inference on one or more other sequential input samples among the sequential input samples using affine transformation based on the layer contraction parameters determined with respect to the reference sample.

    PROXIMITY SENSOR AND PROXIMITY SENSING METHOD USING LIGHT QUANTITY OF REFLECTION LIGHT
    3.
    发明申请
    PROXIMITY SENSOR AND PROXIMITY SENSING METHOD USING LIGHT QUANTITY OF REFLECTION LIGHT 有权
    使用光反射光量的近似传感器和近似感测方法

    公开(公告)号：US20140022528A1

    公开(公告)日：2014-01-23

    申请号：US13940349

    申请日：2013-07-12

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jun Haeng LEE ,  Hyun Surk RYU ,  Kyoobin LEE ,  Tobi DELBRUCK ,  Raphael BERNER

    IPC: G01C3/02

    CPC classification number: G01C3/02 ,  G01S17/026 ,  G06F3/011 ,  H03K17/941 ,  H03K2217/94108 ,  H03K2217/94116

    Abstract: A proximity sensor and proximity sensing method using a change in light quantity of a reflected light are disclosed. The proximity sensor may include a quantity change detection unit which detects a change in a quantity of reflected light which is output light which has been reflected by an object, where an intensity of the output light changes, and a proximity determination unit which determines a proximity of the object to the quantity change detection unit based on a change in the intensity of the output light and the detected change in the quantity of the reflected light.

    Abstract translation: 公开了一种使用反射光的光量变化的接近传感器和接近感测方法。 接近传感器可以包括量变化检测单元，其检测被输出光反射的光的反射光的量的变化，其中输出光的强度改变;以及接近度确定单元，其确定接近度 基于输出光的强度的变化和检测到的反射光量的变化，将物体的数量改变到量变化检测单元。

    METHOD AND APPARATUS WITH NEURAL NETWORK LAYER CONTRACTION
    4.
    发明申请
    METHOD AND APPARATUS WITH NEURAL NETWORK LAYER CONTRACTION 有权

    公开(公告)号：US20250013862A1

    公开(公告)日：2025-01-09

    申请号：US18891591

    申请日：2024-09-20

    Applicant: Samsung Electronics Co., Ltd. ,  University of Zurich

    Inventor： Shih-Chii LIU ,  Bodo RUECKAUER ,  Tobi DELBRUCK

    IPC: G06N3/063 ,  G06N3/082 ,  G06N5/046

    Abstract: A processor-implemented neural network method includes: determining a reference sample among sequential input samples to be processed by a neural network, the neural network comprising an input layer, one or more hidden layers, and an output layer; performing an inference process of obtaining an output activation of the output layer based on operations in the hidden layers corresponding to the reference sample input to the input layer; determining layer contraction parameters for determining an affine transformation relationship between the input layer and the output layer, for approximation of the inference process; and performing inference on one or more other sequential input samples among the sequential input samples using affine transformation based on the layer contraction parameters determined with respect to the reference sample.

    INTERFACE NEURAL NETWORK
    5.
    发明申请
    INTERFACE NEURAL NETWORK 审中-公开

    公开(公告)号：US20170300813A1

    公开(公告)日：2017-10-19

    申请号：US15247160

    申请日：2016-08-25

    Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  UNIVERSITAET ZUERICH

    Inventor： Jun Haeng LEE ,  Tobi DELBRUCK ,  Eric Hyunsurk RYU

    IPC: G06N3/08

    CPC classification number: G06N3/0454

    Abstract: An operation method of a neural network, a training method, and a signal processing apparatus are provided. The operation method includes receiving an output signal from a first neural network, and converting a first feature included in the output signal to a second feature configured to be input to a second neural network, based on a conversion rule controlling conversion between a feature to be output from the first neural network and a feature to be input to the second neural network. The operation method further includes generating an input signal to be input to the second neural network, based on the second feature, and transmitting the input signal to the second neural network.

    EVENT-BASED SENSOR AND OPERATING METHOD OF PROCESSOR
    6.
    发明申请
    EVENT-BASED SENSOR AND OPERATING METHOD OF PROCESSOR 审中-公开
    基于事件的传感器和处理器的操作方法

    公开(公告)号：US20160274643A1

    公开(公告)日：2016-09-22

    申请号：US14862274

    申请日：2015-09-23

    Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Universitaet Zuerich

    Inventor： Hongjie LIU ,  Chenghan LI ,  Christian BRANDLI ,  Shih-Chii LIU ,  Tobi DELBRUCK

    IPC: G06F1/32 ,  G06F3/01

    CPC classification number: G06F1/3215 ,  G06F1/3262 ,  G06F3/005 ,  G06F3/017 ,  G06F3/0416 ,  G06F3/042

    Abstract: An event-based sensor is provided and may include a sensor configured to generate an event signal that includes identification information that relates to an active pixel that detects an event from among a plurality of sensing pixels, a determiner configured to determine whether the event signal is to be filtered based on a predetermined condition, and an outputter configured to output the event signal based on a result of the determination.

    Abstract translation: 提供基于事件的传感器，并且可以包括传感器，其被配置为生成事件信号，该事件信号包括与从多个感测像素中检测到事件的有源像素相关的识别信息;被配置为确定事件信号是否为 基于预定条件进行滤波，以及输出器，被配置为基于确定的结果来输出事件信号。

    INTERFACE NEURAL NETWORK
    8.
    发明申请
    INTERFACE NEURAL NETWORK 有权

    公开(公告)号：US20210056394A1

    公开(公告)日：2021-02-25

    申请号：US17091837

    申请日：2020-11-06

    Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  UNIVERSITAET ZUERICH

    Inventor： Jun Haeng LEE ,  Tobi DELBRUCK ,  Eric Hyunsurk RYU

    IPC: G06N3/04

    Abstract: An operation method of a neural network, a training method, and a signal processing apparatus are provided. The operation method includes receiving an output signal from a first neural network, and converting a first feature included in the output signal to a second feature configured to be input to a second neural network, based on a conversion rule controlling conversion between a feature to be output from the first neural network and a feature to be input to the second neural network. The operation method further includes generating an input signal to be input to the second neural network, based on the second feature, and transmitting the input signal to the second neural network.

Patent Agency Ranking