中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.03 seconds)

    INTERPRETABLE IMITATION LEARNING VIA PROTOTYPICAL OPTION DISCOVERY
    1.
    发明申请
    INTERPRETABLE IMITATION LEARNING VIA PROTOTYPICAL OPTION DISCOVERY 审中-公开

    公开(公告)号：WO2021242585A1

    公开(公告)日：2021-12-02

    申请号：PCT/US2021/033107

    申请日：2021-05-19

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： YU, Wenchao ,  CHEN, Haifeng ,  CHENG, Wei

    IPC: G06N20/00

    Abstract: A method for learning prototypical options for interpretable imitation learning is presented. The method includes initializing (701) options by bottleneck state discovery, each of the options presented by an instance of trajectories generated by experts, applying (703) segmentation embedding learning to extract features to represent current states in segmentations by dividing the trajectories into a set of segmentations, learning (705) prototypical options for each segment of the set of segmentations to mimic expert policies by minimizing loss of a policy and projecting prototypes to the current states, training (707) option policy with imitation learning techniques to learn a conditional policy, generating (709) interpretable policies by comparing the current states in the segmentations to one or more prototypical option embeddings, and taking (711) an action based on the interpretable policies generated.

    PEPTIDE-BASED VACCINE GENERATION SYSTEM
    3.
    发明申请
    PEPTIDE-BASED VACCINE GENERATION SYSTEM 审中-公开

    公开(公告)号：WO2021211233A1

    公开(公告)日：2021-10-21

    申请号：PCT/US2021/021849

    申请日：2021-03-11

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： MIN, Renqiang ,  YU, Wenchao ,  GRAF, Hans, Peter ,  DURDANOVIC, Igor

    IPC: G16B35/10 ,  G16B30/10 ,  G16H50/80

    Abstract: A method is provided for peptide-based vaccine generation. The method receives (210) a dataset of positive and negative binding peptide sequences. The method pre-trains (240) a set of peptide binding property predictors on the dataset to generate training data. The method trains (250) a Wasserstein Generative Adversarial Network (WGAN) only on the positive binding peptide sequences, in which a discriminator of the WGAN is updated to distinguish generated peptide sequences from sampled positive peptide sequences from the training data, and a generator of the WGAN is updated to fool the discriminator. The method trains (260) the WGAN only on the positive binding peptide sequences while simultaneously updating the generator to minimize a kernel Maximum Mean Discrepancy (MMD) loss between the generated peptide sequences and the sampled peptide sequences and maximize prediction accuracies of a set of pre-trained peptide binding property predictors with parameters of the set of pre-trained peptide binding property predictors being fixed.

    GRAPH-BASED PREDICTIVE MAINTENANCE
    4.
    发明申请
    GRAPH-BASED PREDICTIVE MAINTENANCE 审中-公开

    公开(公告)号：WO2020086355A1

    公开(公告)日：2020-04-30

    申请号：PCT/US2019/056498

    申请日：2019-10-16

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： YU, Wenchao ,  NI, Jingchao ,  ZONG, Bo ,  CHENG, Wei ,  CHEN, Haifeng ,  TANG, LuAn

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Systems and methods for predicting system device failure are provided. The method includes performing (740) graph-based predictive maintenance (GBPM) to determine a trained ensemble classification model for detecting maintenance ready components that includes extracted node features and graph features. The method includes constructing (750), based on testing data and the trained ensemble classification model, an attributed temporal graph and the extracted node features and graph features. The method further includes concatenating (760) the extracted node features and graph features. The method also includes determining (770), based on the trained ensemble classification model, a list of prediction results of components that are to be scheduled for component maintenance.

    PERFORMANCE PREDICTION FROM COMMUNICATION DATA
    5.
    发明申请
    PERFORMANCE PREDICTION FROM COMMUNICATION DATA 审中-公开

    公开(公告)号：WO2020076444A1

    公开(公告)日：2020-04-16

    申请号：PCT/US2019/049907

    申请日：2019-09-06

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： CHENG, Wei ,  TANG, LuAn ,  SONG, Dongjin ,  ZONG, Bo ,  CHEN, Haifeng ,  NI, Jingchao ,  YU, Wenchao

    IPC: H04L29/06 ,  G06F21/55 ,  G06N3/08

    Abstract: Systems and methods for predicting system device failure are provided. The method includes representing (610) device failure related data associated with the devices from a predetermined domain by temporal graphs for each of the devices. The method also includes extracting (620) vector representations based on temporal graph features from the temporal graphs that capture both temporal and structural correlation in the device failure related data. The method further includes predicting (650), based on the vector representations and device failure related metrics in the predetermined domain, one or more of the devices that is expected to fail within a predetermined time.

    HIERARCHICAL MULTI-AGENT IMITATION LEARNING WITH CONTEXTUAL BANDITS
    7.
    发明申请
    HIERARCHICAL MULTI-AGENT IMITATION LEARNING WITH CONTEXTUAL BANDITS 审中-公开

    公开(公告)号：WO2021162953A1

    公开(公告)日：2021-08-19

    申请号：PCT/US2021/016846

    申请日：2021-02-05

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： YU, Wenchao ,  CHENG, Wei ,  CHENG, Wei

    IPC: G06N20/00

    Abstract: A computer-implemented method is provided for hierarchical multi-agent imitation learning. The method includes learning (510) sub-policies for sub-tasks of a hierarchical multi-agent imitation learning task by imitating expert trajectories of expert demonstrations of the subtasks with guidance from a high-level policy corresponding to the hierarchical multi-agent imitation learning task. The method further includes collecting (520) feedback from the sub-policies relating to updating the high-level-policy with a new observation. The method also includes updating (530) the high-level policy with the new observation responsive to the feedback from the sub-policies. The high-level policy is configured as a contextual multi-arm bandit that sequentially selects k best sub-policies at each of a plurality of time steps based on contextual information derived from the expert demonstrations (510).

    DYNAMIC GRAPH ANALYSIS
    8.
    发明申请
    DYNAMIC GRAPH ANALYSIS 审中-公开

    公开(公告)号：WO2020060854A1

    公开(公告)日：2020-03-26

    申请号：PCT/US2019/050974

    申请日：2019-09-13

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： TANG, LuAn ,  NI, Jingchao ,  CHENG, Wei ,  CHEN, Haifeng ,  SONG, Dongjin ,  ZONG, Bo ,  YU, Wenchao

    IPC: H04L29/06 ,  G06F21/55 ,  G06N3/08

    Abstract: Systems and methods for implementing dynamic graph analysis (DGA) to detect anomalous network traffic are provided. The method includes processing (510) communications and profile data associated with multiple devices to determine dynamic graphs. The method includes generating (520) features to model temporal behaviors of network traffic generated by the multiple devices based on the dynamic graphs. The method also includes formulating (550) a list of prediction results for sources of the anomalous network traffic from the multiple devices based on the temporal behaviors.

    META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY
    10.
    发明申请
    META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY 审中-公开

    公开(公告)号：WO2022039920A1

    公开(公告)日：2022-02-24

    申请号：PCT/US2021/044268

    申请日：2021-08-03

    Applicant: NEC LABORATORIES AMERICA, INC.

    Inventor： YU, Wenchao ,  CHENG, Wei ,  CHEN, Haifeng ,  SUN, Yiwei

    IPC: G06N20/00 ,  G06N3/08

    Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning (1001) to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning (1003) relationships between the skills that are transferrable across the different tasks, employing (1005), via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating (1007) policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

Patent Agency Ranking