利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

88 条记录 (耗时 0.045 秒)

    SYSTEM AND METHOD FOR LEARNING SPARSE FEATURES FOR SELF-SUPERVISED LEARNING WITH CONTRASTIVE DUAL GATING
    61.
    发明公开
    SYSTEM AND METHOD FOR LEARNING SPARSE FEATURES FOR SELF-SUPERVISED LEARNING WITH CONTRASTIVE DUAL GATING 审中-公开

    公开(公告)号：US20240232718A9

    公开(公告)日：2024-07-11

    申请号：US18494330

    申请日：2023-10-25

    申请人： Jae-sun Seo ,  Jian Meng ,  Li Yang ,  Deliang Fan

    发明人： Jae-sun Seo ,  Jian Meng ,  Li Yang ,  Deliang Fan

    IPC分类号： G06N20/00

    CPC分类号： G06N20/00

    摘要： A method of training a machine learning algorithm comprises providing a set of input data, performing transforms on the input data to generate augmented data, to provide transformed base paths into machine learning algorithm encoders, segmenting the augmented data, calculating main base path outputs by applying a weighting to the segmented augmented data, calculating pruning masks from the input and augmented data to apply to the base paths of the machine learning algorithm encoders, the pruning masks having a binary value for each segment in the segmented augmented data, calculating sparse conditional path outputs by performing a computation on the segments of the segmented augmented data, and calculating a final output as a sum of the main base path outputs and the sparse conditional path outputs. A computer-implemented system for learning sparse features of a dataset is also disclosed.

    METHOD AND SYSTEM FOR A TEMPERATURE-RESILIENT NEURAL NETWORK TRAINING MODEL
    62.
    发明公开
    METHOD AND SYSTEM FOR A TEMPERATURE-RESILIENT NEURAL NETWORK TRAINING MODEL 审中-公开

    公开(公告)号：US20240095528A1

    公开(公告)日：2024-03-21

    申请号：US18463778

    申请日：2023-09-08

    申请人： Jae-sun Seo ,  Jian Meng ,  Li Yang ,  Deliang Fan

    发明人： Jae-sun Seo ,  Jian Meng ,  Li Yang ,  Deliang Fan

    IPC分类号： G06N3/08 ,  G06N3/0495

    CPC分类号： G06N3/08 ,  G06N3/0495

    摘要： A method for increasing the temperature-resiliency of a neural network, the method comprising loading a neural network model into a resistive nonvolatile in-memory-computing chip, training the deep neural network model using a progressive knowledge distillation algorithm as a function of a teacher model, the algorithm comprising injecting, using a clean model as the teacher model, low-temperature noise values into a student model and changing, now using the student model as the teacher model, the low-temperature noises to high-temperature noises, and training the deep neural network model using a batch normalization adaptation algorithm, wherein the batch normalization adaptation algorithm includes training a plurality of batch normalization parameters with respect to a plurality of thermal variations.

    All in one toddler cup with snack container, straw and handle
    63.
    外观设计
    All in one toddler cup with snack container, straw and handle 有权

    公开(公告)号：USD1012615S1

    公开(公告)日：2024-01-30

    申请号：US29822254

    申请日：2022-01-07

    申请人： Li Yang

    设计人： Li Yang

    摘要： FIG. 1 is a front perspective view of an all in one toddler cup with snack container, straw and handle, showing my new design;
    FIG. 2 is a front view thereof;
    FIG. 3 is a rear view thereof;
    FIG. 4 is a left side view thereof;
    FIG. 5 is a right side view thereof;
    FIG. 6 is a top view thereof; and,
    FIG. 7 is a bottom view thereof.

    SYSTEM AND METHOD FOR ROBUST NEURAL NETWORKING VIA NOISE INJECTION
    64.
    发明申请
    SYSTEM AND METHOD FOR ROBUST NEURAL NETWORKING VIA NOISE INJECTION 有权

    公开(公告)号：US20230078473A1

    公开(公告)日：2023-03-16

    申请号：US17932104

    申请日：2022-09-14

    申请人： Deliang Fan ,  Adnan Siraj Rakin ,  Li Yang ,  Chaitali Chakrabarti ,  Yu Cao ,  Jae-sun Seo ,  Jingtao Li

    发明人： Deliang Fan ,  Adnan Siraj Rakin ,  Li Yang ,  Chaitali Chakrabarti ,  Yu Cao ,  Jae-sun Seo ,  Jingtao Li

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： A robust and accurate binary neural network, referred to as RA-BNN, is provided to simultaneously defend against adversarial noise injection and improve accuracy. Recently developed adversarial weight attack, a.k.a. bit-flip attack (BFA), has shown enormous success in compromising deep neural network (DNN) performance with an extremely small amount of model parameter perturbation. To defend against this threat, embodiments of RA-BNN adopt a complete binary neural network (BNN) to significantly improve DNN model robustness (defined as the number of bit-flips required to degrade the accuracy to as low as a random guess). To improve clean inference accuracy, a novel and efficient two-stage network growing method is proposed and referred to as early growth. Early growth selectively grows the channel size of each BNN layer based on channel-wise binary masks training with Gumbel-Sigmoid function. Apart from recovering the inference accuracy, the RA-BNN after growing also shows significantly higher resistance to BFA.

    Cigar humidor
    65.
    外观设计
    Cigar humidor 有权

    公开(公告)号：USD943823S1

    公开(公告)日：2022-02-15

    申请号：US29778339

    申请日：2021-04-13

    申请人： Li Yang

    设计人： Li Yang