中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

109 records (took 0.024 seconds)

    Word embedding system
    101.
    发明授权
    Word embedding system 有权

    公开(公告)号：US10789942B2

    公开(公告)日：2020-09-29

    申请号：US16163988

    申请日：2018-10-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dinghan Shen

    IPC: G10L15/16 ,  G10L15/18 ,  G06N3/04 ,  G10L15/06 ,  G10L15/22 ,  G06N3/08 ,  G06F40/30

    Abstract: A computer-implemented method, computer program product, and computer processing system are provided for word embedding. The method includes receiving, by a processor device, a word embedding matrix. The method further includes generating, by a processor device, an average pooling vector and a max pooling vector, based on the word embedding matrix. The method also includes generating, by the processor device, a prediction by applying a Multi-Layer Perceptron (MLP) to the average pooling vector and the max pooling vector.

    MULTI-SCALE TEXT FILTER CONDITIONED GENERATIVE ADVERSARIAL NETWORKS
    102.
    发明申请
    MULTI-SCALE TEXT FILTER CONDITIONED GENERATIVE ADVERSARIAL NETWORKS 审中-公开

    公开(公告)号：US20200097766A1

    公开(公告)日：2020-03-26

    申请号：US16577337

    申请日：2019-09-20

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Bing Bai ,  Yogesh Balaji

    IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06F17/27

    Abstract: Systems and methods for processing video are provided. The method includes receiving a text-based description of active scenes and representing the text-based description as a word embedding matrix. The method includes using a text encoder implemented by neural network to output frame level textual representation and video level representation of the word embedding matrix. The method also includes generating, by a shared generator, frame by frame video based on the frame level textual representation, the video level representation and noise vectors. A frame level and a video level convolutional filter of a video discriminator are generated to classify frames and video of the frame by frame video as true or false. The method also includes training a conditional video generator that includes the text encoder, the video discriminator, and the shared generator in a generative adversarial network to convergence.

    REAL-TIME DEEP LEARNING FOR DANGER PREDICTION USING HETEROGENEOUS TIME-SERIES SENSOR DATA
    105.
    发明申请
    REAL-TIME DEEP LEARNING FOR DANGER PREDICTION USING HETEROGENEOUS TIME-SERIES SENSOR DATA 审中-公开

    公开(公告)号：US20170286826A1

    公开(公告)日：2017-10-05

    申请号：US15375408

    申请日：2016-12-12

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dongjin Song

    IPC: G06N3/04 ,  G05D1/00 ,  G06N3/08

    CPC classification number: G06N3/0445 ,  B60W40/00 ,  G06N3/0454

    Abstract: A computer-implemented method and a system are provided for, in turn, providing driver assistance for a vehicle. The method includes forming, by a processor, a deep High-Order Long Short-Term Memory (HOLSTM)-based model by applying, to a HOLSTM, high-order interactions captured between global pattern distribution probabilities and local feature representations of an input sensor signal vector at each of a plurality of time steps. The input sensor signal vector is formed from multiple time series. Each of the multiple time series corresponds to a different one of a plurality of driving related sensors. The method further includes generating, by the processor, one or more predictions of impending dangerous conditions related to driving the vehicle based on the deep HOLSTM-based model. The method also includes informing, by an operator-perceptable warning device, an operator of the vehicle of the one or more predictions of impending dangerous conditions.

    SYSTEM AND METHOD FOR FAULT-TOLERANT PARALLEL LEARNING OVER NON-IID DATA
    106.
    发明申请
    SYSTEM AND METHOD FOR FAULT-TOLERANT PARALLEL LEARNING OVER NON-IID DATA 审中-公开

    公开(公告)号：US20170111234A1

    公开(公告)日：2017-04-20

    申请号：US15296560

    申请日：2016-10-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Asim Kadav ,  Renqiang Min ,  Erik Kruus ,  Cun Mu

    IPC: H04L12/24 ,  G06N99/00

    CPC classification number: H04L41/16 ,  G06N99/005 ,  H04L41/147

    Abstract: A network device, system, and method are provided. The network device includes a processor. The processor is configured to store a local estimate and a dual variable maintaining an accumulated subgradient for the network device. The processor is further configured to collect values of the dual variable of neighboring network devices. The processor is also configured to form a convex combination with equal weight from the collected dual variable of neighboring network devices. The processor is additionally configured to add a most recent local subgradient for the network device, scaled by a scaling factor, to the convex combination to obtain an updated dual variable. The processor is further configured to update the local estimate by projecting the updated dual variable to a primal space.

    Corrected Mean-Covariance RBMs and General High-Order Semi-RBMs for Large-Scale Collaborative Filtering and Prediction
    107.
    发明申请
    Corrected Mean-Covariance RBMs and General High-Order Semi-RBMs for Large-Scale Collaborative Filtering and Prediction 审中-公开
    校正平均协方差RBM和一般高阶半RBM用于大规模协同过滤和预测

    公开(公告)号：US20160300134A1

    公开(公告)日：2016-10-13

    申请号：US15088312

    申请日：2016-04-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Eric Cosatto

    IPC: G06N3/08 ,  G06N5/04

    CPC classification number: G06N3/0472 ,  G06N3/0445

    Abstract: Systems and methods are disclosed for operating a Restricted Boltzmann Machine (RBM) by determining a corrected energy function of high-order semi-RBMs (hs-RBMs) without self-interaction; performing distributed pre-training of the hs-RBM; adjusting weights of the hs-RBM using contrastive divergence; generating predictions by Gibbs Sampling or by determining conditional probabilities with hidden units integrated out; and generating predictions.

    Abstract translation: 公开了通过在没有自相互作用的情况下确定高阶半RBM（hs-RBM）的校正能量函数来操作限制玻尔兹曼机器（RBM）的系统和方法; 执行hs-RBM的分布式预训练; 使用对比分歧调整hs-RBM的权重; 通过Gibbs Sampling产生预测，或通过确定隐藏的单位来确定条件概率; 并产生预测。

    Fast Distributed Nonnegative Matrix Factorization and Completion for Big Data Analytics
    108.
    发明申请
    Fast Distributed Nonnegative Matrix Factorization and Completion for Big Data Analytics 审中-公开
    快速分布式非负矩阵因子分解和大数据分析完成

    公开(公告)号：US20160275416A1

    公开(公告)日：2016-09-22

    申请号：US15063236

    申请日：2016-03-07

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dongjin Song

    IPC: G06N99/00

    CPC classification number: G06N99/005 ,  G05B13/04 ,  G06F17/16

    Abstract: Systems and methods are disclosed for operating a machine, by receiving training data from one or more sensors; training a machine learning module with the training data by: partitioning a data matrix into smaller submatrices to process in parallel and optimized for each processing node; for each submatrix, performing a greedy search for rank-one solutions; using alternating direction method of multipliers (ADMM) to ensure consistency over different data blocks; and controlling one or more actuators using live data and the learned module during operation.

    Abstract translation: 公开了通过从一个或多个传感器接收训练数据来操作机器的系统和方法; 通过以下方式训练具有训练数据的机器学习模块：将数据矩阵分割成更小的子矩阵以并行处理并针对每个处理节点进行优化; 对于每个子矩阵，对第一级解决方案执行贪婪搜索; 使用乘法器的交替方向法（ADMM）来确保不同数据块的一致性; 并且在操作期间使用实时数据和所学习的模块控制一个或多个致动器。

    SPARSE HIGHER-ORDER MARKOV RANDOM FIELD
    109.
    发明申请
    SPARSE HIGHER-ORDER MARKOV RANDOM FIELD 有权
    稀疏的MARKOV随机场

    公开(公告)号：US20130325786A1

    公开(公告)日：2013-12-05

    申请号：US13908715

    申请日：2013-06-03

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Yanjun Qi

    IPC: G06N5/02

    CPC classification number: G06N5/025

    Abstract: Systems and methods are provided for identifying combinatorial feature interactions, including capturing statistical dependencies between categorical variables, with the statistical dependencies being stored in a computer readable storage medium. A model is selected based on the statistical dependencies using a neighborhood estimation strategy, with the neighborhood estimation strategy including generating sets of arbitrarily high-order feature interactions using at least one rule forest and optimizing one or more likelihood functions. A damped mean-field approach is applied to the model to obtain parameters of a Markov random field (MRF); a sparse high-order semi-restricted MRF is produced by adding a hidden layer to the MRF; indirect long-range dependencies between feature groups are modeled using the sparse high-order semi-restricted MRF; and a combinatorial dependency structure between variables is output.

    Abstract translation: 提供了用于识别组合特征交互的系统和方法，包括捕获分类变量之间的统计依赖性，并将统计依赖性存储在计算机可读存储介质中。 基于使用邻域估计策略的统计依赖性来选择模型，邻域估计策略包括使用至少一个规则林生成任意高阶特征交互的集合并优化一个或多个似然函数。 将阻尼平均场方法应用于模型以获得马尔可夫随机场（MRF）的参数; 通过向MRF添加隐藏层来产生稀疏高阶半限制MRF; 特征组之间的间接长程依赖关系使用稀疏高阶半限制MRF进行建模; 并输出变量之间的组合依赖结构。

Patent Agency Ranking