DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwang, Sung Ju | ko |
dc.contributor.author | Lee, Haebum | ko |
dc.contributor.author | Na, Donghyun | ko |
dc.contributor.author | Yang, Eunho | ko |
dc.date.accessioned | 2023-12-01T05:02:19Z | - |
dc.date.available | 2023-12-01T05:02:19Z | - |
dc.identifier.uri | http://hdl.handle.net/10203/315561 | - |
dc.description.abstract | A method for generating a trained model is provided. The method for generating a trained model includes: receiving a learning data; generating an asymmetric multi-task feature network including a parameter matrix of the trained model which permits an asymmetric knowledge transfer between tasks and a feedback matrix for a feedback connection from the tasks to features; computing a parameter matrix of the asymmetric multi-task feature network using the input learning data to minimize a predetermined objective function; and generating an asymmetric multi-task feature trained model using the computed parameter matrix as the parameter of the generated asymmetric multi-task feature network. | - |
dc.title | Electronic apparatus and method for generating trained model | - |
dc.title.alternative | 전자 장치 및 학습 모델 생성 방법 | - |
dc.type | Patent | - |
dc.type.rims | PAT | - |
dc.contributor.localauthor | Hwang, Sung Ju | - |
dc.contributor.localauthor | Yang, Eunho | - |
dc.contributor.nonIdAuthor | Lee, Haebum | - |
dc.contributor.assignee | KAIST | - |
dc.identifier.iprsType | 특허 | - |
dc.identifier.patentApplicationNumber | 16002614 | - |
dc.identifier.patentRegistrationNumber | 11645508 | - |
dc.date.application | 2018-06-07 | - |
dc.date.registration | 2023-05-09 | - |
dc.publisher.country | US | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.