中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

156 records (took 0.025 seconds)

    Computer code refactoring
    71.
    发明授权
    Computer code refactoring 有权

    公开(公告)号：US11782703B2

    公开(公告)日：2023-10-10

    申请号：US17739727

    申请日：2022-05-09

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xuchao Zhang ,  Haifeng Chen ,  Wei Cheng

    IPC: G06F8/72 ,  G06F8/30

    CPC classification number: G06F8/72 ,  G06F8/30

    Abstract: Systems and methods are provided for automated computer code editing. The method includes training a code-editing neural network model using a corpus of code editing data samples, including the pre-editing samples and post-editing samples, and parsing the pre-editing samples and post-editing samples into an Abstract Syntax Tree (AST). The method further includes using a grammar specification to transform the AST tree into a unified Abstract Syntax Description Language (ASDL) graph for different programming languages, and using a gated graph neural network (GGNN) to compute a vector representation for each node in the unified Abstract Syntax Description Language (ASDL) graph. The method further includes selecting and aggregating support samples based on a query code with a multi-extent ensemble method, and altering the query code iteratively using the pattern learned from the pre- and post-editing samples.

    DYNAMIC CAUSAL DISCOVERY IN IMITATION LEARNING
    73.
    发明申请
    DYNAMIC CAUSAL DISCOVERY IN IMITATION LEARNING 有权

    公开(公告)号：US20230080424A1

    公开(公告)日：2023-03-16

    申请号：US17877081

    申请日：2022-07-29

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wenchao Yu ,  Wei Cheng ,  Haifeng Chen ,  Yuncong Chen ,  Xuchao Zhang ,  Tianxiang Zhao

    IPC: G06N7/00

    Abstract: A method for learning a self-explainable imitator by discovering causal relationships between states and actions is presented. The method includes obtaining, via an acquisition component, demonstrations of a target task from experts for training a model to generate a learned policy, training the model, via a learning component, the learning component computing actions to be taken with respect to states, generating, via a dynamic causal discovery component, dynamic causal graphs for each environment state, encoding, via a causal encoding component, discovered causal relationships by updating state variable embeddings, and outputting, via an output component, the learned policy including trajectories similar to the demonstrations from the experts.

    Self-attentive attributed network embedding
    74.
    发明授权
    Self-attentive attributed network embedding 有权

    公开(公告)号：US11544530B2

    公开(公告)日：2023-01-03

    申请号：US16662754

    申请日：2019-10-24

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wei Cheng ,  Wenchao Yu ,  Haifeng Chen

    IPC: G06N3/04 ,  G06K9/62 ,  G06N20/00

    Abstract: Methods and systems for determining a network embedding include training a network embedding model using training data that includes topology information for networks and attribute information relating to vertices of the networks. An embedded representation is generated using the trained network embedding model to represent an input network, with associated attribute information, in a network topology space. A machine learning task is performed using the embedded representation as input to a machine learning model.

    INTERPRETABLE IMITATION LEARNING VIA PROTOTYPICAL OPTION DISCOVERY
    79.
    发明申请
    INTERPRETABLE IMITATION LEARNING VIA PROTOTYPICAL OPTION DISCOVERY 有权

    公开(公告)号：US20210374612A1

    公开(公告)日：2021-12-02

    申请号：US17323475

    申请日：2021-05-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wenchao Yu ,  Haifeng Chen ,  Wei Cheng

    IPC: G06N20/00

    Abstract: A method for learning prototypical options for interpretable imitation learning is presented. The method includes initializing options by bottleneck state discovery, each of the options presented by an instance of trajectories generated by experts, applying segmentation embedding learning to extract features to represent current states in segmentations by dividing the trajectories into a set of segmentations, learning 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 option policy with imitation learning techniques to learn a conditional policy, generating interpretable policies by comparing the current states in the segmentations to one or more prototypical option embeddings, and taking an action based on the interpretable policies generated.

    HIERARCHICAL MULTI-AGENT IMITATION LEARNING WITH CONTEXTUAL BANDITS
    80.
    发明申请
    HIERARCHICAL MULTI-AGENT IMITATION LEARNING WITH CONTEXTUAL BANDITS 有权

    公开(公告)号：US20210248465A1

    公开(公告)日：2021-08-12

    申请号：US17167890

    申请日：2021-02-04

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wenchao Yu ,  Haifeng Chen ,  Wei Cheng

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A computer-implemented method is provided for hierarchical multi-agent imitation learning. The method includes learning 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 feedback from the sub-policies relating to updating the high-level-policy with a new observation. The method also includes updating 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

Patent Agency Ranking