知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

23 条记录 (耗时 0.016 秒)

    INTERPRETING AND IMPROVING THE PROCESSING RESULTS OF RECURRENT NEURAL NETWORKS
    3.
    发明申请
    INTERPRETING AND IMPROVING THE PROCESSING RESULTS OF RECURRENT NEURAL NETWORKS 有权

    公开(公告)号：US20210182657A1

    公开(公告)日：2021-06-17

    申请号：US16710080

    申请日：2019-12-11

    申请人： INAIT SA

    发明人： Henry Markram ,  Felix Schürmann ,  John Rahmon ,  Daniel Milan Lütgehetmann ,  Constantin Cosmin Atanasoaei

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： A method includes defining a plurality of different windows of time in a recurrent artificial neural network, wherein each of the different windows has different durations, has different start times, or has both different durations and different start times, identifying occurrences of topological patterns of activity in the recurrent artificial neural network in the different windows of time, comparing the occurrences of the topological patterns of activity in the different windows, and classifying, based on a result of the comparison, a first decision that is represented by a first topological pattern of activity that occurs in a first of the windows as less robust than a second decision that is represented by a second topological pattern of activity that occurs in a second of the windows.

    INPUT INTO A NEURAL NETWORK
    5.
    发明公开
    INPUT INTO A NEURAL NETWORK 审中-公开

    公开(公告)号：US20240046077A1

    公开(公告)日：2024-02-08

    申请号：US18490927

    申请日：2023-10-20

    申请人： INAIT SA

    发明人： Henry Markram ,  Felix Schürmann ,  Fabien Jonathan Delalondre ,  Daniel Milan Lütgehetmann ,  John Rahmon

    IPC分类号： G06N3/047 ,  G06F17/18 ,  G06N3/045

    CPC分类号： G06N3/047 ,  G06F17/18 ,  G06N3/045

    摘要： Abstracting data that originates from different sensors and transducers using artificial neural networks. A method can include identifying topological patterns of activity in a recurrent artificial neural network and outputting a collection of digits. The topological patterns are responsive to an input, into the recurrent artificial neural network, of first data originating from a first sensor and second data originating from a second sensor. Each topological pattern abstracts a characteristic shared by the first data and the second data. The first and second sensors sense different data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.

    INTERPRETING AND IMPROVING THE PROCESSING RESULTS OFRECURRENT NEURAL NETWORKS
    6.
    发明公开
    INTERPRETING AND IMPROVING THE PROCESSING RESULTS OFRECURRENT NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230316077A1

    公开(公告)日：2023-10-05

    申请号：US18295969

    申请日：2023-04-05

    申请人： INAIT SA

    发明人： Henry Markram ,  Felix Schuermann ,  John Rahmon ,  Daniel Milan Lütgehetmann ,  Constantin Cosmin Atanasoaei

    IPC分类号： G06N3/08 ,  G06N3/049 ,  G06N3/044

    CPC分类号： G06N3/08 ,  G06N3/044 ,  G06N3/049

    摘要： A method includes defining a plurality of different windows of time in a recurrent artificial neural network, wherein each of the different windows has different durations, has different start times, or has both different durations and different start times, identifying occurrences of topological patterns of activity in the recurrent artificial neural network in the different windows of time, comparing the occurrences of the topological patterns of activity in the different windows, and classifying, based on a result of the comparison, a first decision that is represented by a first topological pattern of activity that occurs in a first of the windows as less robust than a second decision that is represented by a second topological pattern of activity that occurs in a second of the windows.

    Annotation of 3D models with signs of use visible in 2D images
    10.
    发明授权
    Annotation of 3D models with signs of use visible in 2D images 有权

    公开(公告)号：US11544914B2

    公开(公告)日：2023-01-03

    申请号：US17190646

    申请日：2021-03-03

    申请人： INAIT SA

    发明人： Constantin Cosmin Atanasoaei ,  Daniel Milan Lütgehetmann ,  Dimitri Zaganidis ,  John Rahmon ,  Michele De Gruttola

    IPC分类号： G06T19/20 ,  G06T7/73 ,  G06T7/90

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for annotation of 3D models with signs of use that are visible in 2D images. In one aspect, methods are performed by data processing apparatus. The methods can include projecting signs of use in a relatively larger field of view image of an instance of an object onto a 3D model of the object based on a pose of the instance in the relatively larger field of view image, and estimating a relative pose of the instance of the object in a relatively smaller field of view image based on matches between the signs of use in the relatively larger field of view image and the same signs of use in the relatively smaller field of view image.