中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

120 records (took 0.028 seconds)

    Quantifying vulnerabilities of deep learning computing systems to adversarial perturbations
    113.
    发明授权
    Quantifying vulnerabilities of deep learning computing systems to adversarial perturbations 有权

    公开(公告)号：US11227215B2

    公开(公告)日：2022-01-18

    申请号：US16296897

    申请日：2019-03-08

    Applicant: International Business Machines Corporation

    Inventor： Sijia Liu ,  Quanfu Fan ,  Chuang Gan ,  Dakuo Wang

    IPC: G06N3/08 ,  G06N20/00

    Abstract: Mechanisms are provided for generating an adversarial perturbation attack sensitivity (APAS) visualization. The mechanisms receive a natural input dataset and a corresponding adversarial attack input dataset, where the adversarial attack input dataset comprises perturbations intended to cause a misclassification by a computer model. The mechanisms determine a sensitivity measure of the computer model to the perturbations in the adversarial attack input dataset based on a processing of the natural input dataset and corresponding adversarial attack input dataset by the computer model. The mechanisms generate a classification activation map (CAM) for the computer model based on results of the processing and a sensitivity overlay based on the sensitivity measure. The sensitivity overlay graphically represents different classifications of perturbation sensitivities. The mechanisms apply the sensitivity overlay to the CAM to generate and output a graphical visualization output of the computer model sensitivity to perturbations of adversarial attacks.

    Gradient-embedded video anomaly detection
    114.
    发明授权
    Gradient-embedded video anomaly detection 有权

    公开(公告)号：US11210775B1

    公开(公告)日：2021-12-28

    申请号：US17025639

    申请日：2020-09-18

    Applicant: International Business Machines Corporation

    Inventor： Bo Wu ,  Chuang Gan ,  Dakuo Wang ,  Rameswar Panda

    IPC: G06K9/00 ,  G06T7/00 ,  G06T7/269 ,  G06N3/08

    Abstract: A sequence of frames of a video can be received. For a given frame in the sequence of frames, a gradient-embedded frame is generated corresponding to the given frame. The gradient-embedded frame incorporates motion information. The motion information can be represented as disturbance in the gradient-embedded frame. A plurality of such gradient-embedded frames can be generated corresponding to a plurality of the sequence of frames. Based on the plurality of gradient-embedded frames, a neural network such as a generative adversarial network is trained to learn to suppress the disturbance in the gradient-embedded frame and to generate a substitute frame. In inference stage, anomaly in a target video frame can be detected by comparing it to a corresponding substitute frame generated by the neural network.

    Framework for few-shot temporal action localization
    115.
    发明授权
    Framework for few-shot temporal action localization 有权

    公开(公告)号：US11164039B2

    公开(公告)日：2021-11-02

    申请号：US16661501

    申请日：2019-10-23

    Applicant: International Business Machines Corporation

    Inventor： Chuang Gan ,  Ming Tan ,  Yang Zhang ,  Dakuo Wang

    IPC: G06K9/62 ,  G06K9/46 ,  G06N3/08

    Abstract: Systems and techniques that facilitate few-shot temporal action localization based on graph convolutional networks are provided. In one or more embodiments, a graph component can generate a graph that models a support set of temporal action classifications. Nodes of the graph can correspond to respective temporal action classifications in the support set. Edges of the graph can correspond to similarities between the respective temporal action classifications. In various embodiments, a convolution component can perform a convolution on the graph, such that the nodes of the graph output respective matching scores indicating levels of match between the respective temporal action classifications and an action to be classified. In various embodiments, an instantiation component can input into the nodes respective input vectors based on a proposed feature vector representing the action to be classified. In various cases, the respective temporal action classifications can correspond to respective example feature vectors, and the respective input vectors can be concatenations of the respective example feature vectors and the proposed feature vector.

    TRANSFER LEARNING ACROSS AUTOMATED MACHINE LEARNING SYSTEMS
    116.
    发明申请
    TRANSFER LEARNING ACROSS AUTOMATED MACHINE LEARNING SYSTEMS 有权

    公开(公告)号：US20210271966A1

    公开(公告)日：2021-09-02

    申请号：US16806626

    申请日：2020-03-02

    Applicant: International Business Machines Corporation

    Inventor： Dakuo Wang ,  Ming Tan ,  Chuang Gan ,  Jason Tsay ,  Gregory Bramble

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Techniques regarding transferring learning outcomes across machine learning tasks in automated machine learning systems are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that can executes a machine learning task using an existing artificial intelligence model on a sample dataset based on a similarity between the sample dataset and a historical dataset. The existing artificial intelligence model can be generated by automated machine learning and trained on the historical dataset.

    INTENT CLASSIFICATION DISTRIBUTION CALIBRATION
    118.
    发明申请
    INTENT CLASSIFICATION DISTRIBUTION CALIBRATION 有权

    公开(公告)号：US20210049502A1

    公开(公告)日：2021-02-18

    申请号：US16543117

    申请日：2019-08-16

    Applicant: International Business Machines Corporation

    Inventor： Haoyu Wang ,  Ming Tan ,  Dakuo Wang ,  Chuang Gan ,  Saloni Potdar

    IPC: G06N20/00 ,  G06F16/28 ,  G06N7/00

    Abstract: A method includes determining, based on an input data sample, a set of probabilities. Each probability of the set of probabilities is associated with a respective label of a set of labels. A particular probability associated with a particular label indicates an estimated likelihood that the input data sample is associated with the particular label. The method includes modifying the set of probabilities based on a set of adjustment factors to generate a modified set of probabilities. The set of adjustment factors is based on a first relative frequency distribution and a second relative frequency distribution. The first relative frequency distribution indicates for each label of the set of labels, a frequency of occurrence of the label among training data. The second relative frequency distribution indicates for each label of the set of labels, a frequency of occurrence of the label among post-training data provided to the trained classifier.

Patent Agency Ranking