知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

43 条记录 (耗时 0.02 秒)

    TRAINING A STUDENT NEURAL NETWORK TO MIMIC A MENTOR NEURAL NETWORK WITH INPUTS THAT MAXIMIZE STUDENT-TO-MENTOR DISAGREEMENT
    1.
    发明公开
    TRAINING A STUDENT NEURAL NETWORK TO MIMIC A MENTOR NEURAL NETWORK WITH INPUTS THAT MAXIMIZE STUDENT-TO-MENTOR DISAGREEMENT 审中-公开

    公开(公告)号：US20240220807A1

    公开(公告)日：2024-07-04

    申请号：US18603363

    申请日：2024-03-13

    申请人： NANO DIMENSION TECHNOLOGIES, LTD.

    发明人： Eli DAVID ,  Eri RUBIN

    IPC分类号： G06N3/086 ,  G06N3/044

    CPC分类号： G06N3/086 ,  G06N3/044

    摘要： A device, system, and method is provided for training a new neural network to mimic a target neural network without access to the target neural network or its original training dataset. The target neural network and the new neural network may be probed with input data to generate corresponding target and new output data. Input data may be detected that generate a maximum or above threshold difference between the corresponding target and new output data. A divergent probe training dataset may be generated comprising the input data that generate the maximum or above threshold difference and the corresponding target output data. The new neural network may be trained using the divergent probe training dataset to generate the target output data. The new neural network may be iteratively trained using an updated divergent probe training dataset dynamically adjusted as the new neural network changes during training.

    System and method for efficient evolution of deep convolutional neural networks using filter-wise recombination and propagated mutations
    2.
    发明授权
    System and method for efficient evolution of deep convolutional neural networks using filter-wise recombination and propagated mutations 有权

    公开(公告)号：US11710044B2

    公开(公告)日：2023-07-25

    申请号：US16458517

    申请日：2019-07-01

    申请人： Nano Dimension Technologies, Ltd.

    发明人： Eli David

    IPC分类号： G06N3/08 ,  G06N3/086 ,  G06N3/045

    CPC分类号： G06N3/086 ,  G06N3/045

    摘要： An efficient technique of machine learning is provided for training a plurality of convolutional neural networks (CNNs) with increased speed and accuracy using a genetic evolutionary model. A plurality of artificial chromosomes may be stored representing weights of artificial neuron connections of the plurality of respective CNNs. A plurality of pairs of the chromosomes may be recombined to generate, for each pair, a new chromosome (with a different set of weights than in either chromosome of the pair) by selecting entire filters as inseparable groups of a plurality of weights from each of the pair of chromosomes (e.g., “filter-by-filter” recombination). A plurality of weights of each of the new or original plurality of chromosomes may be mutated by propagating recursive error corrections incrementally throughout the CNN. A small random sampling of weights may optionally be further mutated to zero, random values, or a sum of current and random values.

    SYSTEM AND METHOD FOR MIMICKING A NEURAL NETWORK WITHOUT ACCESS TO THE ORIGINAL TRAINING DATASET OR THE TARGET MODEL
    7.
    发明公开
    SYSTEM AND METHOD FOR MIMICKING A NEURAL NETWORK WITHOUT ACCESS TO THE ORIGINAL TRAINING DATASET OR THE TARGET MODEL 审中-公开

    公开(公告)号：US20240232635A1

    公开(公告)日：2024-07-11

    申请号：US18442718

    申请日：2024-02-15

    申请人： NANO DIMENSION TECHNOLOGIES, LTD.

    发明人： Eli DAVID

    IPC分类号： G06N3/086 ,  G06N3/04 ,  G06N3/084

    CPC分类号： G06N3/086 ,  G06N3/04 ,  G06N3/084

    摘要： A device, system, and method is provided to mimic a pre-trained target model without access to the pre-trained target model or its original training dataset. A set of random or semi-random input data may be sent to randomly probe the pre-trained target model at a remote device. A set of corresponding output data may be received from the remote device that is generated by applying the pre-trained target model to the set of random or semi-random input data. A random probe training dataset may be generated comprising the set of random or semi-random input data and corresponding output data generated by randomly probing the pre-trained target model. A new model may be trained with the random probe training dataset so that the new model generates substantially the same corresponding output data in response to said input data to mimic the pre-trained target model.

    INKJET PRINT HEADS CLEANING SYSTEM
    9.
    发明申请
    INKJET PRINT HEADS CLEANING SYSTEM 有权

    公开(公告)号：US20220088930A1

    公开(公告)日：2022-03-24

    申请号：US17441997

    申请日：2020-03-23

    申请人： Nano Dimension Technologies LTD.

    发明人： Tomer Friedman ,  Salamon Mekonen

    IPC分类号： B41J2/165

    摘要： The disclosure relates to a portable system for cleaning ink jet print heads. Specifically, the disclosure relates to external, portable systems and jig assemblies for cleaning clogged nozzles of ink jet print head under controlled pressure. The jig assembly can be self-contained and detachable, and can be programmed to operate upon receiving various signals indicating clogged nozzle plate or portion thereof, and/or as a routine maintenance operating procedure.