中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.015 seconds)

    DECRYPTION-LESS PRIVACY PROTECTION USING A TRANSFORM IN THE IMAGER
    1.
    发明公开
    DECRYPTION-LESS PRIVACY PROTECTION USING A TRANSFORM IN THE IMAGER 审中-公开

    公开(公告)号：US20230394637A1

    公开(公告)日：2023-12-07

    申请号：US18206001

    申请日：2023-06-05

    Applicant: SRI International

    Inventor： David Chao ZHANG ,  Michael A. ISNARDI ,  Michael R. PIACENTINO

    IPC: G06T5/10 ,  G06V20/52

    CPC classification number: G06T5/10 ,  G06V20/52 ,  G06V2201/07

    Abstract: A method, apparatus and system for image privacy protection and actionable response includes distorting an analog image captured using an image capture device in a residential, industrial or commercial environment using a transform filter, digitizing the distorted analog image, analyzing the distorted, digitized image using a trained machine learning process to identify at least one of an individual or an object in the distorted, digitized image, the machine learning process having been trained to identify individuals and objections in the distorted image, and upon identification of at least one of an individual or an object in the distorted image for which action is to be taken, communicating an indication to at least one device in the residential, commercial or industrial environment to cause the device to perform a predetermined action.

    SYSTEM DESIGN FOR AN INTEGRATED LIFELONG MACHINE LEARNING AGENT
    3.
    发明公开
    SYSTEM DESIGN FOR AN INTEGRATED LIFELONG MACHINE LEARNING AGENT 审中-公开

    公开(公告)号：US20240202538A1

    公开(公告)日：2024-06-20

    申请号：US18535928

    申请日：2023-12-11

    Applicant: SRI International

    Inventor： Aswin NADAMUNI RAGHAVAN ,  Indranil SUR ,  Zachary DANIELS ,  Jesse HOSTETLER ,  Abrar RAHMAN ,  Ajay DIVAKARAN ,  Michael R. PIACENTINO

    IPC: G06N3/092

    CPC classification number: G06N3/092

    Abstract: A method, apparatus and system for lifelong reinforcement learning include receiving features of a task, communicating the task features to a learning system, where the learning system learns or performs a task related to the features based on learning or performing similar previous tasks, determining from the features if the task has changed and if so, communicating the features of the changed task to the learning system, where the learning system learns or performs the changed task based on learning or performing similar previous tasks, automatically annotating feature characteristics of received features including differences between the features of the original task and the features of the changed task to enable the learning system to more efficiently learn or perform at least the changed task, and if the task has not changed, processing the task features of a current task by the learning system to learn or perform the current task.

    METHODS FOR ENHANCED IMAGING BASED ON SEMANTIC PROCESSING AND DYNAMIC SCENE MODELING
    4.
    发明申请
    METHODS FOR ENHANCED IMAGING BASED ON SEMANTIC PROCESSING AND DYNAMIC SCENE MODELING 有权

    公开(公告)号：US20210160422A1

    公开(公告)日：2021-05-27

    申请号：US17044245

    申请日：2018-10-01

    Applicant: SRI INTERNATIONAL

    Inventor： Michael R. PIACENTINO ,  John R. TOWER ,  Michael A. ISNARDI ,  Sek M. CHAI

    IPC: H04N5/232

    Abstract: Modules and control units cooperate to simultaneously and independently control and adjust pixel parameters non-uniformly at regional increments across an entire image captured in an image frame by pixels in a pixel array. Pixel parameter changes for pixels in a given region occur, based on i) a contextual understanding of what contextually was happening in the one or more prior image frames and ii) whether salient items are located within that region. Additionally, guidance is sent to the sensor control unit to i) increase or decrease pixel parameters within those regions with salient items and then either to i) maintain, ii) increase or iii) decrease pixel parameters within regions without salient items in order to stay within any i) bandwidth limitations ii) memory storage, and/or iii) power consumptions limitations imposed by 1) one or more image sensors or 2) the communication loop between the sensor control unit and the image processing unit.

    EDGE DEVICE HAVING A HETEROGENOUS NEUROMORPHIC COMPUTING ARCHITECTURE
    6.
    发明申请
    EDGE DEVICE HAVING A HETEROGENOUS NEUROMORPHIC COMPUTING ARCHITECTURE 有权

    公开(公告)号：US20220198782A1

    公开(公告)日：2022-06-23

    申请号：US17553239

    申请日：2021-12-16

    Applicant: SRI International

    Inventor： David Chao ZHANG ,  Michael R. PIACENTINO ,  Aswin NADAMUNI RAGHAVAN

    IPC: G06V10/774 ,  G06N3/04 ,  G06N3/08

    Abstract: An edge device comprising a feature extractor and a reconfigurator. The feature extractor comprises a first neural network for encoding input information into data vectors and extracting particular data vectors representing features within the input information, wherein the first neural network comprises at least one encoder layer and at least one adaptor layer. The reconfigurator is coupled to the feature extractor and comprises a second neural network for classifying the particular data vectors and wherein, upon requiring additional features to be extracted, the reconfigurator adapts at least one layer in the first neural network, second neural network or both by performing at least one of: (1) altering weights, (2) adding layers, (3) deleting layers, (4) reordering layers to improve classification of particular data vector. The first neural network, the second neural network or both are trained using gradient-free training.

Patent Agency Ranking