中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

86 records (took 0.034 seconds)

    Histogram-based per-layer data format selection for hardware implementation of deep neural network
    51.
    发明授权
    Histogram-based per-layer data format selection for hardware implementation of deep neural network 有权

    公开(公告)号：US11593626B2

    公开(公告)日：2023-02-28

    申请号：US16180536

    申请日：2018-11-05

    Applicant: Imagination Technologies Limited

    Inventor： James Imber ,  Cagatay Dikici

    IPC: G06N3/063 ,  G06F7/499 ,  G06F7/544 ,  G06N3/04

    Abstract: A histogram-based method of selecting a fixed point number format for representing a set of values input to, or output from, a layer of a Deep Neural Network (DNN). The method comprises obtaining a histogram that represents an expected distribution of the set of values of the layer, each bin of the histogram is associated with a frequency value and a representative value in a floating point number format; quantising the representative values according to each of a plurality of potential fixed point number formats; estimating, for each of the plurality of potential fixed point number formats, the total quantisation error based on the frequency values of the histogram and a distance value for each bin that is based on the quantisation of the representative value for that bin; and selecting the fixed point number format associated with the smallest estimated total quantisation error as the optimum fixed point number format for representing the set of values of the layer.

    Error Allocation Format Selection for Hardware Implementation of Deep Neural Network
    53.
    发明申请
    Error Allocation Format Selection for Hardware Implementation of Deep Neural Network 有权

    公开(公告)号：US20210125047A1

    公开(公告)日：2021-04-29

    申请号：US17141349

    申请日：2021-01-05

    Applicant: Imagination Technologies Limited

    Inventor： James Imber

    IPC: G06N3/063 ,  G06N3/08 ,  G06F7/483 ,  G06F17/11

    Abstract: Methods for determining a fixed point format for one or more layers of a DNN based on the portion of the output error of the DNN attributed to the fixed point formats of the different layers. Specifically, in the methods described herein the output error of a DNN attributable to the quantisation of the weights or input data values of each layer is determined using a Taylor approximation and the fixed point number format of one or more layers is adjusted based on the attribution. For example, where the fixed point number formats used by a DNN comprises an exponent and a mantissa bit length, the mantissa bit length of the layer allocated the lowest portion of the output error may be reduced, or the mantissa bit length of the layer allocated the highest portion of the output error may be increased. Such a method may be iteratively repeated to determine an optimum set of fixed point number formats for the layers of a DNN.

    Error Allocation Format Selection for Hardware Implementation of Deep Neural Network
    54.
    发明申请
    Error Allocation Format Selection for Hardware Implementation of Deep Neural Network 审中-公开

    公开(公告)号：US20190227893A1

    公开(公告)日：2019-07-25

    申请号：US16181104

    申请日：2018-11-05

    Applicant: Imagination Technologies Limited

    Inventor： James Imber

    IPC: G06F11/22 ,  G06N3/08

    Abstract: Methods for determining a fixed point format for one or more layers of a DNN based on the portion of the output error of the DNN attributed to the fixed point formats of the different layers. Specifically, in the methods described herein the output error of a DNN attributable to the quantisation of the weights or input data values of each layer is determined using a Taylor approximation and the fixed point number format of one or more layers is adjusted based on the attribution. For example, where the fixed point number formats used by a DNN comprises an exponent and a mantissa bit length, the mantissa bit length of the layer allocated the lowest portion of the output error may be reduced, or the mantissa bit length of the layer allocated the highest portion of the output error may be increased. Such a method may be iteratively repeated to determine an optimum set of fixed point number formats for the layers of a DNN.

    Systems and methods for processing images of objects using lighting keyframes
    55.
    发明授权
    Systems and methods for processing images of objects using lighting keyframes 有权

    公开(公告)号：US10185888B2

    公开(公告)日：2019-01-22

    申请号：US15335607

    申请日：2016-10-27

    Applicant: Imagination Technologies Limited

    Inventor： James Imber ,  Adrian Hilton ,  Jean-Yves Guillemaut

    IPC: G06K9/46 ,  G06T7/90 ,  G06T15/50

    Abstract: An image processing system and method for determining an intrinsic color component of one or more objects present in a sequence of frames, for use in rendering the object(s), is described. At least some of the frames of the sequence are to be used as lighting keyframes. A lighting estimate for a lighting keyframe A of the sequence of frames is obtained. An initial lighting estimate for a lighting keyframe B of the sequence of frames is determined. A refined lighting estimate for the lighting keyframe B is determined based on: (i) the initial lighting estimate for the lighting keyframe B, and (ii) the lighting estimate for the lighting keyframe A. The refined lighting estimate for the lighting keyframe B is used to separate image values representing the object(s) in the lighting keyframe B into an intrinsic color component and a shading component, for use in rendering the object(s).

    Convolutional Neural Network Hardware Configuration
    59.
    发明申请
    Convolutional Neural Network Hardware Configuration 审中-公开

    公开(公告)号：US20170323197A1

    公开(公告)日：2017-11-09

    申请号：US15585645

    申请日：2017-05-03

    Applicant: Imagination Technologies Limited

    Inventor： Clifford Gibson ,  James Imber

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

    Abstract: A method of configuring a hardware implementation of a Convolutional Neural Network (CNN), the method comprising: determining, for each of a plurality of layers of the CNN, a first number format for representing weight values in the layer based upon a distribution of weight values for the layer, the first number format comprising a first integer of a first predetermined bit-length and a first exponent value that is fixed for the layer; determining, for each of a plurality of layers of the CNN, a second number format for representing data values in the layer based upon a distribution of expected data values for the layer, the second number format comprising a second integer of a second predetermined bit-length and a second exponent value that is fixed for the layer; and storing the determined number formats for use in configuring the hardware implementation of a CNN.

Patent Agency Ranking