利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

183 条记录 (耗时 0.022 秒)

    SEMI-SUPERVISED FRAMEWORK FOR EFFICIENT TIME-SERIES ORDINAL CLASSIFICATION
    61.
    发明公开
    SEMI-SUPERVISED FRAMEWORK FOR EFFICIENT TIME-SERIES ORDINAL CLASSIFICATION 审中-公开

    公开(公告)号：US20230252302A1

    公开(公告)日：2023-08-10

    申请号：US18152238

    申请日：2023-01-10

    申请人： NEC Laboratories America, Inc.

    发明人： Liang Tong ,  Takehiko Mizoguchi ,  Zhengzhang Chen ,  Wei Cheng ,  Haifeng Chen ,  Nauman Ahad

    IPC分类号： G06N3/0895 ,  G06N3/0442

    CPC分类号： G06N3/0895 ,  G06N3/0442

    摘要： A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k−1 binary classifiers on top of the semi-supervised representations to obtain k−1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k−1 binary predictions by matching the inconsistent ones to consistent ones of the k−1 binary predictions. The method further includes aggregating the k−1 binary predictions to obtain an ordinal prediction.

    Systems, Methods and Devices for Map-Based Object's Localization Deep Learning and Object's Motion Trajectories on Geospatial Maps Using Neural Network
    62.
    发明公开
    Systems, Methods and Devices for Map-Based Object's Localization Deep Learning and Object's Motion Trajectories on Geospatial Maps Using Neural Network 审中-公开

    公开(公告)号：US20230243658A1

    公开(公告)日：2023-08-03

    申请号：US18004614

    申请日：2021-07-06

    申请人： Ohio State Innovation Foundation

    发明人： Alper Yilmaz ,  Bing Zha

    IPC分类号： G01C21/30 ,  G01C21/16 ,  G06N3/0442 ,  G06N3/063

    CPC分类号： G01C21/30 ,  G01C21/1656 ,  G06N3/0442 ,  G06N3/063

    摘要： An object of initial unknown position on a map may be determined by traversing through moving and turning to establish motion trajectory to reduce its spatial uncertainty to a single location that would fit only to a certain map trajectory. A artificial neural network model learns from object motion on different map topologies may establish the object's end-to-end positioning from embedding map topologies and object motion. The proposed method includes learning potential motion patterns from the map and perform trajectory classification in the map's edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and both a Graph Neural Network and an RNN are trained from the map for each representation to compare their performances. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize the object based on its motion trajectories.

    KNOWLEDGE GRAPH CONSTRUCTION METHOD FOR ETHYLENE OXIDE DERIVATIVES PRODUCTION PROCESS
    64.
    发明公开
    KNOWLEDGE GRAPH CONSTRUCTION METHOD FOR ETHYLENE OXIDE DERIVATIVES PRODUCTION PROCESS 审中-公开

    公开(公告)号：US20230169309A1

    公开(公告)日：2023-06-01

    申请号：US17992775

    申请日：2022-11-22

    申请人： DALIAN UNIVERSITY OF TECHNOLOGY

    发明人： Xin YANG ,  Xiaopeng WEI ,  Li ZHU ,  Xirong XU ,  Chenming DUAN

    IPC分类号： G06N3/042 ,  G06N3/0442

    CPC分类号： G06N3/042 ,  G06N3/0442

    摘要： The present invention belongs to the technical field of knowledge graph, and provides a knowledge graph construction method for an ethylene oxide derivatives production process. According to data types and characteristics, data sources of the ethylene oxide derivatives production process are sorted and divided into three types: structural data, unstructured data and other types of data. An ontology layer and a data layer of a knowledge graph are constructed by combining top-down and bottom-up methods. A data-driven incremental ontology modeling method is proposed to ensure the expandability of the knowledge graph. For structural knowledge extraction, the safety of original data storage is ensured by means of virtual knowledge graph, and a new mapping mechanism is proposed to realize data materialization. For unstructured knowledge extraction, an entity extraction task is realized on the basis of a BERT-BiLSTM-CRF named entity recognition model by integrating a pre-training language model BERT.

    Energy-Efficient Recurrent Neural Network Accelerator
    65.
    发明公开
    Energy-Efficient Recurrent Neural Network Accelerator 审中-公开

    公开(公告)号：US20240354548A1

    公开(公告)日：2024-10-24

    申请号：US18302154

    申请日：2023-04-18

    申请人： Taiwan Semiconductor Manufacturing Company, Ltd.

    发明人： Kerem Akarvardar ,  Yu-Der Chih ,  Xiaoyu Sun

    IPC分类号： G06N3/0442 ,  G06N3/048

    CPC分类号： G06N3/0442 ,  G06N3/048

    摘要： Systems and methods are provided for a neural network that includes a multiply accumulate (MAC) unit that is configured to receive an input vector weight matrix; multiply the input matrix by the input vector weight matrix, generating input vector partial sums; receive time-delayed hidden vectors and a hidden vector weight matrix; and multiply the time-delayed hidden vectors and the hidden vector weight matrix, which generates hidden vector partial sums. An accumulator may be coupled to the MAC unit and configured to accumulate and add the input vector partial sums and the hidden vector partial sums, generating full sum vectors. The neural network may generate the time-delayed hidden vectors based on the full sum vectors. The neural network may further include a first selection device coupled to the MAC unit that is configured to select between the input matrix and the time-delayed hidden vectors for reception at the MAC unit.

    HARDWARE REALIZATION OF NEURAL NETWORKS USING BUFFERS
    66.
    发明公开
    HARDWARE REALIZATION OF NEURAL NETWORKS USING BUFFERS 审中-公开

    公开(公告)号：US20240346302A1

    公开(公告)日：2024-10-17

    申请号：US18135100

    申请日：2023-04-14

    申请人： PolyN Technology Limited

    发明人： Nikolai KOVSHOV ,  Boris Maslov ,  Aleksandrs Timofejevs ,  Dmitri Godovskiy

    IPC分类号： G06N3/065 ,  G06N3/0442

    CPC分类号： G06N3/065 ,  G06N3/0442

    摘要： A method for hardware realization of neural networks executes at a computing device. The device obtains a neural network topology for a trained convolutional neural network that transforms a set of input tensors and generates a set of intermediate tensors. The device computes a measure of locality for tensors of the trained convolutional neural network based on dependencies between the set of input tensors and the set of intermediate tensors. The device transforms the trained convolutional neural network into an equivalent buffered neural network that includes a left subnetwork and a right subnetwork based on the neural network topology and the measure of locality. The left subnetwork and the right subnetwork are interconnected via a buffer. The device generates a schematic model for implementing the equivalent buffered neural network, including selecting component parameter values for neurons of the equivalent buffered neural network and connections between the neurons.

    GROUND SENSING PLUG FOR DETERMINING THE AMOUNT OF ELECTROSTATIC DISCHARGE USING A NEURAL NETWORK
    67.
    发明公开
    GROUND SENSING PLUG FOR DETERMINING THE AMOUNT OF ELECTROSTATIC DISCHARGE USING A NEURAL NETWORK 审中-公开

    公开(公告)号：US20240319255A1

    公开(公告)日：2024-09-26

    申请号：US18326320

    申请日：2023-05-31

    申请人： Worldhomedoctor Corp.

    发明人： Jiyoun KIM

    IPC分类号： G01R31/14 ,  G01R29/12 ,  G06N3/0442 ,  G06N3/08 ,  H01R13/66

    CPC分类号： G01R31/14 ,  G01R29/12 ,  G06N3/0442 ,  G06N3/08 ,  H01R13/665 ,  H01R13/7175 ,  H01R24/68 ,  H01R2103/00 ,  H01R2201/20

    摘要： Embodiments present a ground sensing plug for determining the amount of electrostatic discharge using a neural network. The ground sensing plug may include a first plug terminal configured to receive power from a power outlet connected thereto, a second plug terminal configured to have two recesses exposed to an outside to perform a function of an earth terminal, a controller including at least one processor, a memory, a communication unit, and circuitry electrically connected to the first plug terminal and the second plug terminal, and a display including a display panel and a plurality of light emitting diodes electrically connected to the circuitry, the plurality of light emitting diodes including a first light emitting diode, a second light emitting diode, and a plurality of third light emitting diodes, and emit green light based on a grounded state being detected, and a housing arranged to enclose the controller.

    TEST CASE PRIORITIZATION
    69.
    发明公开
    TEST CASE PRIORITIZATION 审中-公开

    公开(公告)号：US20240303185A1

    公开(公告)日：2024-09-12

    申请号：US18180484

    申请日：2023-03-08

    申请人： Microsoft Technology Licensing, LLC

    发明人： Laurent BOUÉ ,  Kiran RAMA

    IPC分类号： G06F11/36 ,  G06N3/0442 ,  G06N3/08

    CPC分类号： G06F11/3688 ,  G06N3/0442 ,  G06N3/08

    摘要： A computing system encodes a next graph based on modified source code files recorded by the next code commit event. The computing system inputs the next graph to a graph machine learning model, the graph machine learning model being trained by graphs representing modified source code files and software test results corresponding to multiple code commit events occurring prior to the next code commit event in the sequence of code commit events. The computing system determines an order of test cases of the next code commit event using the graph machine learning model in an inference mode. The computing system executes the test cases according to the order during the software development build process corresponding to the next code commit event.