中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.018 seconds)

    TRAIN-ONCE-FOR-ALL PERSONALIZATION
    1.
    发明公开
    TRAIN-ONCE-FOR-ALL PERSONALIZATION 审中-公开

    公开(公告)号：US20240362460A1

    公开(公告)日：2024-10-31

    申请号：US18626833

    申请日：2024-04-04

    Applicant: Google LLC

    Inventor： Li Zhang ,  Yandong Li ,  Yin Cui ,  Hong-You Chen ,  Mingda Zhang

    IPC: G06N3/0455 ,  G06N3/084

    CPC classification number: G06N3/0455 ,  G06N3/084

    Abstract: The technology relates to providing personalized neural network-based models according to user input, which can be generated upon request or otherwise as needed. This may include receiving, by one or more processors of a computing device, input corresponding to a task description. Then the input corresponding to the task description is encoded into a set of text embeddings. Based on this, the system applies mixer prediction to the set of text embeddings to generate a set of mixers and learns a set of basis models according to the set of mixers. The set of basis models are combined to form a single personalized model corresponding to the task description. This personalized model can then be used in video understanding, quality assessment, providing a recommendation, performing a classification, or performing a search.

    Personalized Federated Learning Via Sharable Basis Models
    2.
    发明公开
    Personalized Federated Learning Via Sharable Basis Models 审中-公开

    公开(公告)号：US20240119307A1

    公开(公告)日：2024-04-11

    申请号：US18474934

    申请日：2023-09-26

    Applicant: Google LLC

    Inventor： Hong-You Chen ,  Boqing Gong ,  Mingda Zhang ,  Hang Qi ,  Xuhui Jia ,  Li Zhang

    IPC: G06N3/098

    CPC classification number: G06N3/098

    Abstract: The embodiments are directed towards providing personalized federated learning (PFL) models via sharable federated basis models. A model architecture and learning algorithm for PFL models is disclosed. The embodiments learn a set of basis models, which can be combined layer by layer to form a personalized model for each client using specifically learned combination coefficients. The set of basis models are shared with each client of a set of the clients. Thus, the set of basis models is common to each client of the set of clients. However, each client may generate a unique PFL based on their specifically learned combination coefficients. The unique combination of coefficients for each client may be encoded in a separate personalized vector for each of the clients.

    Training User-Level Differentially Private Machine-Learned Models
    6.
    发明申请
    Training User-Level Differentially Private Machine-Learned Models 审中-公开

    公开(公告)号：US20190227980A1

    公开(公告)日：2019-07-25

    申请号：US15877196

    申请日：2018-01-22

    Applicant: Google LLC

    Inventor： Hugh Brendan McMahan ,  Kunal Talwar ,  Li Zhang ,  Daniel Ramage

    IPC: G06F15/18 ,  G06F8/65 ,  G06K9/62

    Abstract: Systems and methods for learning differentially private machine-learned models are provided. A computing system can include one or more server computing devices comprising one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors cause the one or more server computing devices to perform operations. The operations can include selecting a subset of client computing devices from a pool of available client computing devices; providing a machine-learned model to the selected client computing devices; receiving, from each selected client computing device, a local update for the machine-learned model; determining a differentially private aggregate of the local updates; and determining an updated machine-learned model based at least in part on the data-weighted average of the local updates.

    PRIVACY-ENHANCED TRAINING AND DEPLOYMENT OF MACHINE LEARNING MODELS USING CLIENT-SIDE AND SERVER-SIDE DATA
    7.
    发明公开
    PRIVACY-ENHANCED TRAINING AND DEPLOYMENT OF MACHINE LEARNING MODELS USING CLIENT-SIDE AND SERVER-SIDE DATA 审中-公开

    公开(公告)号：US20240054391A1

    公开(公告)日：2024-02-15

    申请号：US17928372

    申请日：2022-04-05

    Applicant: GOOGLE LLC

    Inventor： Abhradeep Guha Thakurta ,  Li Zhang ,  Prateek Jain ,  Shuang Song ,  Steffen Rendle ,  Steve Shaw-Tang Chien ,  Walid Krichene ,  Yarong Mu

    IPC: G06N20/00 ,  G06F21/62

    CPC classification number: G06N20/00 ,  G06F21/6218

    Abstract: Computer-implemented systems and methods for training a decentralized model for making a personalized recommendation. In one aspect, the method comprising: obtaining, using user activity data, client-side training data that includes features and training labels; and training, by the client device, a decentralized model in training rounds, wherein training, in each training round comprises: receiving, first data including a current server-side embedding generated by the server-side machine learning model, wherein the first data received from the server does not include any server-side data used in generating the current server-side embedding; generating, using the client-side machine learning model, a client-side embedding based on the client-side training data; updating, using the client-side embedding and the current server-side embedding and based on the training labels, the client-side machine learning model; generating, an updated client-side embedding; and transmitting second data including the updated client-side embedding for subsequent updating of the server-side machine learning model.

    Systems and Methods for Providing Feedback for Artificial Intelligence-Based Image Capture Devices
    8.
    发明申请
    Systems and Methods for Providing Feedback for Artificial Intelligence-Based Image Capture Devices 有权

    公开(公告)号：US20220366219A1

    公开(公告)日：2022-11-17

    申请号：US17878724

    申请日：2022-08-01

    Applicant: Google LLC

    Inventor： Aaron Michael Donsbach ,  Christopher Breithaupt ,  Li Zhang ,  Arushan Rajasekaram ,  Navid Shiee

    IPC: G06N3/04 ,  H04N5/232 ,  G06N3/08

    Abstract: The present disclosure provides systems and methods that provide feedback to a user of an image capture device that includes an artificial intelligence system that analyzes incoming image frames to, for example, determine whether to automatically capture and store the incoming frames. An example system can also, in the viewfinder portion of a user interface presented on a display, a graphical intelligence feedback indicator in association with a live video stream. The graphical intelligence feedback indicator can graphically indicate, for each of a plurality of image frames as such image frame is presented within the viewfinder portion of the user interface, a respective measure of one or more attributes of the respective scene depicted by the image frame output by the artificial intelligence system.

    Systems and Methods for Providing Feedback for Artificial Intelligence-Based Image Capture Devices
    9.
    发明申请
    Systems and Methods for Providing Feedback for Artificial Intelligence-Based Image Capture Devices 有权

    公开(公告)号：US20210303968A1

    公开(公告)日：2021-09-30

    申请号：US17266957

    申请日：2019-01-22

    Applicant: Google LLC

    Inventor： Aaron Michael Donsbach ,  Christopher Breithaupt ,  Li Zhang ,  Arushan Rajasekaram ,  Navid Shiee

    IPC: G06N3/04 ,  H04N5/232 ,  G06N3/08

    Abstract: The present disclosure provides systems and methods that provide feedback to a user of an image capture device that includes an artificial intelligence system that analyzes incoming image frames to, for example, determine whether to automatically capture and store the incoming frames. An example system can also, in the viewfinder portion of a user interface presented on a display, a graphical intelligence feedback indicator in association with a live video stream. The graphical intelligence feedback indicator can graphically indicate, for each of a plurality of image frames as such image frame is presented within the viewfinder portion of the user interface, a respective measure of one or more attributes of the respective scene depicted by the image frame output by the artificial intelligence system.

Patent Agency Ranking