DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwang, Sung Ju | ko |
dc.contributor.author | Park, Seong-Jin | ko |
dc.contributor.author | Han, Seungju | ko |
dc.contributor.author | Kim, Insoo | ko |
dc.contributor.author | Baek, Jiwon | ko |
dc.contributor.author | Han, Jaejoon | ko |
dc.date.accessioned | 2024-08-21T03:00:07Z | - |
dc.date.available | 2024-08-21T03:00:07Z | - |
dc.identifier.uri | http://hdl.handle.net/10203/322374 | - |
dc.description.abstract | A processor-implemented neural network method includes: extracting, by a feature extractor of a neural network, a plurality of training feature vectors corresponding to a plurality of training class data of each of a plurality of classes including a first class and a second class; determining, by a feature sample generator of the neural network, an additional feature vector of the second class based on a mean vector and a variation vector of the plurality of training feature vectors of each of the first class and the second class; and training a class vector of the second class included in a classifier of the neural network based on the additional feature vector and the plurality of training feature vectors of the second class. | - |
dc.title | Method and apparatus with neural network meta-training and class vector training | - |
dc.title.alternative | 뉴럴 네트워크의 메타 학습 방법 및 장치와 뉴럴 네트워크의 클래스 벡터 학습 방법 및 장치 | - |
dc.type | Patent | - |
dc.type.rims | PAT | - |
dc.contributor.localauthor | Hwang, Sung Ju | - |
dc.contributor.nonIdAuthor | Park, Seong-Jin | - |
dc.contributor.nonIdAuthor | Han, Seungju | - |
dc.contributor.nonIdAuthor | Kim, Insoo | - |
dc.contributor.nonIdAuthor | Baek, Jiwon | - |
dc.contributor.nonIdAuthor | Han, Jaejoon | - |
dc.contributor.assignee | KAIST, Samsung Electronics Co., Ltd. | - |
dc.identifier.iprsType | 특허 | - |
dc.identifier.patentApplicationNumber | 17119381 | - |
dc.identifier.patentRegistrationNumber | 12039449 | - |
dc.date.application | 2020-12-11 | - |
dc.date.registration | 2024-07-16 | - |
dc.publisher.country | US | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.