Patents Assigned to INEEJI
  • Methods and apparatus for extracting data in deep neural networks
    Patent number: 11829861
    Abstract: Disclosed is a method and apparatus for extracting data in a deep learning model. The method includes receiving an input query, determining a first decision boundary set being a subset of a decision boundary set corresponding to a target layer of the deep learning model, extracting a decision region including the input query based on the first decision boundary set, and extracting data included in the decision region.
    Type: Grant
    Filed: August 30, 2019
    Date of Patent: November 28, 2023
    Assignees: UNIST (ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY), INEEJI
    Inventors: Jae Sik Choi, Hae Dong Jeong, Gi Young Jeon
  • METHODS AND APPARATUS FOR EXTRACTING DATA IN DEEP NEURAL NETWORKS
    Publication number: 20210406643
    Abstract: Disclosed is a method and apparatus for extracting data in a deep learning model. The method includes receiving an input query, determining a first decision boundary set being a subset of a decision boundary set corresponding to a target layer of the deep learning model, extracting a decision region including the input query based on the first decision boundary set, and extracting data included in the decision region.
    Type: Application
    Filed: August 30, 2019
    Publication date: December 30, 2021
    Applicants: UNIST (ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY), INEEJI
    Inventors: Jae Sik CHOI, Hae Dong JEONG, Gi Young JEON