中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

109 records (took 0.025 seconds)

    CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE WITH ADAPTIVE FILTERS
    11.
    发明申请
    CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE WITH ADAPTIVE FILTERS 审中-公开

    公开(公告)号：US20190079915A1

    公开(公告)日：2019-03-14

    申请号：US16038830

    申请日：2018-07-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dinghan Shen ,  Yitong Li

    IPC: G06F17/27 ,  G06N3/04 ,  G06N5/04 ,  G06F17/30 ,  H03M7/30

    Abstract: A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.

    CONTEXT-AWARE ATTENTION-BASED NEURAL NETWORK FOR INTERACTIVE QUESTION ANSWERING
    12.
    发明申请
    CONTEXT-AWARE ATTENTION-BASED NEURAL NETWORK FOR INTERACTIVE QUESTION ANSWERING 审中-公开

    公开(公告)号：US20180121785A1

    公开(公告)日：2018-05-03

    申请号：US15789614

    申请日：2017-10-20

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Asim Kadav ,  Huayu Li

    IPC: G06N3/00 ,  G06N3/04

    CPC classification number: G06N3/006 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/0481 ,  G06N5/04

    Abstract: A context-aware attention-based neural network is provided for answering an input question given a set of purportedly supporting statements for the input question. The neural network includes a processing element. The processing element is configured to calculate a question representation for the input question, based on word annotations and word-level attentions calculated for the input question. The processing element is further configured to calculate a sentence representation for each of the purportedly supporting statements, based on word annotations and word-level attentions calculated for each of the purportedly supporting statements. The processing element is also configured to calculate a context representation for the set of purportedly supporting statements with respect to the sentence representation for each of the purportedly supporting statements. The processing element is additionally configured to generate an answer to the input question based on the question representation and the context representation.

    DEEP HIGH-ORDER EXEMPLAR LEARNING FOR HASHING AND FAST INFORMATION RETRIEVAL
    13.
    发明申请
    DEEP HIGH-ORDER EXEMPLAR LEARNING FOR HASHING AND FAST INFORMATION RETRIEVAL 审中-公开

    公开(公告)号：US20170293838A1

    公开(公告)日：2017-10-12

    申请号：US15478840

    申请日：2017-04-04

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min

    IPC: G06N3/08 ,  G06N5/04 ,  G06F17/30 ,  G06N3/04

    CPC classification number: G06N3/0454

    Abstract: A system and method are provided for deep high-order exemplar learning of a data set. Feature vectors and class labels are received. Each of the feature vectors represents a respective one of a plurality of high-dimensional data points of the data set. The class labels represent classes for the high-dimensional data points. Each of the feature vectors are processed, using a deep high-order convolutional neural network, to obtain respective low-dimensional embedding vectors within each class. A minimization operation is performed on high-order embedding parameters of the high-dimensional data points to output a set of synthetic exemplars. A binarizing operation is performed on the low-dimensional embedding vectors and the set of synthetic exemplars to output hash codes representing the data set. The hash codes are utilized as a search key to increase the efficiency of a processor-based machine searching the data set.

    SCALABLE SUPERVISED HIGH-ORDER PARAMETRIC EMBEDDING FOR BIG DATA VISUALIZATION
    17.
    发明申请
    SCALABLE SUPERVISED HIGH-ORDER PARAMETRIC EMBEDDING FOR BIG DATA VISUALIZATION 审中-公开

    公开(公告)号：US20170236069A1

    公开(公告)日：2017-08-17

    申请号：US15365631

    申请日：2016-11-30

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min

    IPC: G06N99/00 ,  G06F17/30

    CPC classification number: G06N20/00 ,  G06F16/26

    Abstract: A method is provided for scalable supervised high-order parametric embedding for big data visualization. The method is performed by a processor and includes receiving feature vectors and class labels. Each feature vector is representative of a respective one of a plurality of high-dimensional data points. The class labels denote classes for the high-dimensional data points. The method further includes multiplying each feature vector by one or more factorized high-order tensors to obtain respective product vectors. The method also includes performing a maximally collapsing metric learning on the product vectors using learned synthetic exemplars and learned high-order filters. The learned high-order filters represent high-order embedding parameters. The method additionally includes performing an output operation to output a set of data that includes (i) interpretable factorized high-order filters, (ii) exemplars representative of the class labels and data separation properties in two-dimensional space, and (iii) a two-dimensional embedding of the high-dimensional data points.

    Memory Efficient Scalable Deep Learning with Model Parallelization
    18.
    发明申请
    Memory Efficient Scalable Deep Learning with Model Parallelization 审中-公开

    公开(公告)号：US20170116520A1

    公开(公告)日：2017-04-27

    申请号：US15271589

    申请日：2016-09-21

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Huahua Wang ,  Asim Kadav

    IPC: G06N3/08 ,  G06F17/16

    Abstract: Methods and systems for training a neural network include sampling multiple local sub-networks from a global neural network. The local sub-networks include a subset of neurons from each layer of the global neural network. The plurality of local sub-networks are trained at respective local processing devices to produce trained local parameters. The trained local parameters from each local sub-network are averaged to produce trained global parameters.

    High-order sequence kernel methods for peptide analysis
    19.
    发明申请
    High-order sequence kernel methods for peptide analysis 审中-公开
    肽分析的高阶序列核方法

    公开(公告)号：US20160232281A1

    公开(公告)日：2016-08-11

    申请号：US14511495

    申请日：2014-10-10

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Pavel Kuksa

    IPC: G06F19/18 ,  G06N5/04 ,  G06F19/24 ,  G06F19/22

    CPC classification number: G16C99/00

    Abstract: System and methods are disclosed to perform peptide-MHC interaction prediction by applying a high-order kernel function to determine a similarity between peptide sequences; applying one or more supervised strategies to the kernel to encode relevant physicochemical and interaction information about peptide sequence and MHC molecule; and applying a classifier to the kernel to identify the peptide-MHC interaction of interest in response to a query.

    Abstract translation: 公开了通过应用高阶核函数来确定肽序列之间的相似性来进行肽-MHC相互作用预测的系统和方法; 对核心应用一个或多个监督策略来编码关于肽序列和MHC分子的相关物理化学和相互作用信息; 以及将分类器应用于内核以鉴定响应于查询的感兴趣的肽-MHC相互作用。

    KNOWLEDGE-DRIVEN SPARSE LEARNING APPROACH TO IDENTIFYING INTERPRETABLE HIGH-ORDER FEATURE INTERACTIONS FOR SYSTEM OUTPUT PREDICTION
    20.
    发明申请
    KNOWLEDGE-DRIVEN SPARSE LEARNING APPROACH TO IDENTIFYING INTERPRETABLE HIGH-ORDER FEATURE INTERACTIONS FOR SYSTEM OUTPUT PREDICTION 审中-公开
    知识驱动的微小学习方法来识别系统输出预测的可解释的高阶特征交互

    公开(公告)号：US20140309122A1

    公开(公告)日：2014-10-16

    申请号：US14243920

    申请日：2014-04-03

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Yanjun Qi ,  Salim Akhter Chowdhury

    IPC: G06F19/24 ,  G06N99/00

    CPC classification number: G16B40/00 ,  G06N20/00 ,  G16B5/00 ,  G16B50/00

    Abstract: Systems and methods are disclosed for Knowledge-Driven Sparse Learning to Identify Interpretable High-Order Feature Interactions. This is done by generating one or more functional groups from gene features and gene and protein interaction grouping; selecting informative genes and functional interactions that exhibit differential patterns for the target disease and to generate a reduced feature space; and searching exhaustively on the reduced feature space by examining all possible pairs of interacting features (and possibly higher-order feature interactions) to identify combination of markers and complex patterns of feature interactions that are informative about the phenotypes in a sparse learning framework to select informative interactions and genes.

    Abstract translation: 公开了知识驱动的稀疏学习识别可解释的高阶特征交互的系统和方法。 这是通过从基因特征和基因和蛋白质相互作用分组产生一个或多个官能团来实现的; 选择信息性基因和功能相互作用，显示目标疾病的差异模式并产生减少的特征空间; 并通过检查所有可能的交互特征对（以及可能的高阶特征相互作用）来查找减少的特征空间，从而识别标记的组合和特征相互作用的复杂模式，以便在稀疏学习框架中提供关于表型的信息，以选择信息 相互作用和基因。

Patent Agency Ranking