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
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