中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

40 records (took 0.024 seconds)

    Using a generic classifier to train a personalized classifier for wearable devices
    21.
    发明授权
    Using a generic classifier to train a personalized classifier for wearable devices 有权
    使用通用分类器来训练可穿戴设备的个性化分类器

    公开(公告)号：US09563855B2

    公开(公告)日：2017-02-07

    申请号：US14318555

    申请日：2014-06-27

    Applicant: Intel Corporation

    Inventor： Xue Yang ,  Lakshman Krishnamurthy ,  Lama Nachman

    IPC: G06N99/00 ,  G06N5/04

    CPC classification number: G06N99/005 ,  G06F1/163 ,  G06N3/0454 ,  G06N3/08

    Abstract: Systems and methods may provide for using one or more generic classifiers to generate self-training data based on a first plurality of events associated with a device, and training a personal classifier based on the self-training data. Additionally, the one or more generic classifiers and the personal classifier may be used to generate validation data based on a second plurality of events associated with the device. In one example, the personal classifier is substituted for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.

    Abstract translation: 系统和方法可以提供使用一个或多个通用分类器基于与设备相关联的第一多个事件来生成自训练数据，以及基于自训练数据训练个人分类器。 另外，一个或多个通用分类器和个人分类器可以用于基于与设备相关联的第二多个事件来生成验证数据。 在一个示例中，如果验证数据指示个人分类器相对于一个或多个通用分类器满足置信条件，则个人分类器被替换为一个或多个通用分类器。

    NEURAL FEATURE SELECTION AND FEATURE INTERACTION LEARNING
    22.
    发明公开
    NEURAL FEATURE SELECTION AND FEATURE INTERACTION LEARNING 审中-公开

    公开(公告)号：US20230186080A1

    公开(公告)日：2023-06-15

    申请号：US17936975

    申请日：2022-09-30

    Applicant: Intel Corporation

    Inventor： Anthony Rhodes ,  Hong Lu ,  Jose Lopez ,  Lama Nachman

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: Data analysis and neural network training technology includes generates, based on a sparse neural network, a feature selection ranking representing a ranked list of features from input data, where the sparse neural network is a shallow neural network trained with the input data and then pruned, generates, based on the sparse neural network, a feature set dictionary representing interactions among features from the input data, and performs, based on the feature selection ranking and the feature set dictionary, one or more of generating an output analysis of insights from the input data and the sparse neural network, or training of a second neural network. The technology can also adjust the input data based on the feature set ranking to produce adjusted input data, where the sparse neural network is re-trained based on the adjusted input data and then pruned prior to generating the feature set dictionary.

    SYSTEM AND METHOD OF USING FRACTIONAL ADAPTIVE LINEAR UNIT AS ACTIVATION IN ARTIFACIAL NEURAL NETWORK
    24.
    发明申请
    SYSTEM AND METHOD OF USING FRACTIONAL ADAPTIVE LINEAR UNIT AS ACTIVATION IN ARTIFACIAL NEURAL NETWORK 有权

    公开(公告)号：US20220101138A1

    公开(公告)日：2022-03-31

    申请号：US17548692

    申请日：2021-12-13

    Applicant: Intel Corporation

    Inventor： Anthony Daniel Rhodes ,  Julio Cesar Zamora Esquivel ,  Lama Nachman

    IPC: G06N3/08 ,  G06N3/04

    Abstract: An apparatus is provided for deep learning. The apparatus accesses a neural network including an input layer, hidden layers, and an output layer. The apparatus adds an activation function to one or more of the hidden layers of the hidden layers and output layer. The activation function includes a tunable parameter, the value of which can be adjusted during the training of the neural network. The apparatus trains the neural network by inputting training samples into the neural network and determining internal parameters of the neural network based on the training samples. Determining the internal parameters includes determining a value of the tunable parameter based on the training samples. The apparatus may determine two different values of the tunable parameter for two different layers. The activation function may include another tunable parameter. The apparatus can determine a value for the other tunable parameter during the training of the neural network.

    Asynchronous representation of alternate reality characters
    25.
    发明授权
    Asynchronous representation of alternate reality characters 有权

    公开(公告)号：US10319145B2

    公开(公告)日：2019-06-11

    申请号：US13997773

    申请日：2013-03-14

    Applicant: Intel Corporation

    Inventor： Glen Anderson ,  Wendy March ,  Giuseppe Raffa ,  Adam Jordan ,  Yi Wu ,  Rahul C. Shah ,  Lama Nachman ,  Ana P. Rosario

    IPC: G06T19/00 ,  G06T19/20 ,  H04N5/222 ,  G06Q10/10 ,  G06Q50/00 ,  A63F13/65

    Abstract: Technologies for representing alternate reality characters in a real-world environment include receiving sensor data from sensors of a sensor network of a home location of an alternate reality character, determining available response to the stimuli represented by the sensor data, and determining an activity of the alternate reality character for a time period based on the available responses. The technologies may also include generating a video of the alternate reality character performing the determined activity superimposed on an image map of a real-world environment of the home location during the time period. Users may view the video in real time or during a time period subsequent to the time period represented in the video. Additionally, the alternate reality character may be transferred to remote computing devices in some embodiments.

    USING A GENERIC CLASSIFIER TO TRAIN A PERSONALIZED CLASSIFIER FOR WEARABLE DEVICES
    29.
    发明申请
    USING A GENERIC CLASSIFIER TO TRAIN A PERSONALIZED CLASSIFIER FOR WEARABLE DEVICES 审中-公开

    公开(公告)号：US20170178032A1

    公开(公告)日：2017-06-22

    申请号：US15425763

    申请日：2017-02-06

    Applicant: Intel Corporation

    Inventor： Xue Yang ,  Lakshman Krishnamurthy ,  Lama Nachman

    IPC: G06N99/00 ,  G06F1/16

    CPC classification number: G06N20/00 ,  G06F1/163 ,  G06N3/0454 ,  G06N3/08

    Abstract: Systems and methods may provide for using one or more generic classifiers to generate self-training data based on a first plurality of events associated with a device, and training a personal classifier based on the self-training data. Additionally, the one or more generic classifiers and the personal classifier to may be used to generate validation data based on a second plurality of events associated with the device. In one example, the personal classifier is substituted for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.

    CONTEXT-AWARE COLLABORATIVE USER TRACKING
    30.
    发明申请
    CONTEXT-AWARE COLLABORATIVE USER TRACKING 审中-公开
    语境合作用户追踪

    公开(公告)号：US20160337795A1

    公开(公告)日：2016-11-17

    申请号：US15106764

    申请日：2013-12-19

    Applicant: INTEL CORPORATION

    Inventor： Lama Nachman ,  Horst W. Haussecker ,  Jim S. Baca ,  Burges Karkaria

    IPC: H04W4/02 ,  H04W4/20

    CPC classification number: H04W4/023 ,  H04W4/029 ,  H04W4/21

    Abstract: Technologies are presented that provide collaborative context-based user tracking and communications. A method of tracking communication options may include receiving, from one or more user devices of a user, user proximity information that indicates whether the user is in proximity of the one or more user devices; receiving, from the user devices, tracking loss warnings that indicate that loss of capabilities to track the user by respective user devices may be imminent; receiving, from the user devices, secondary device proximity information that indicates whether the user device is in proximity of one or more secondary devices; and receiving, from the secondary devices, additional user proximity information that indicates whether the user is in proximity of the one or more secondary devices. The method may further include dynamically determining from the received information which of the user devices and secondary devices are able to provide communications to the user.

    Abstract translation: 提供了提供基于协作上下文的用户跟踪和通信的技术。 跟踪通信选项的方法可以包括从用户的一个或多个用户设备接收指示用户是否处于一个或多个用户设备附近的用户接近度信息; 从用户设备接收跟踪损失警告，指示由各个用户设备跟踪用户的能力的丢失可能即将到来; 从用户设备接收指示用户设备是否在一个或多个辅助设备附近的辅助设备接近信息; 以及从辅助设备接收附加的用户接近信息，其指示用户是否在一个或多个辅助设备附近。 该方法还可以包括根据接收到的信息来动态地确定用户设备和辅助设备中的哪一个能够向用户提供通信。

Patent Agency Ranking