DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoo, Hoi-Jun | ko |
dc.contributor.author | Han, Donghyeon | ko |
dc.date.accessioned | 2024-04-23T11:00:16Z | - |
dc.date.available | 2024-04-23T11:00:16Z | - |
dc.identifier.uri | http://hdl.handle.net/10203/319211 | - |
dc.description.abstract | Disclosed herein are an apparatus and method for training a deep neural network. An apparatus for training a deep neural network including N layers, each having multiple neurons, includes an error propagation processing unit configured to, when an error occurs in an N-th layer in response to initiation of training of the deep neural network, determine an error propagation value for an arbitrary layer based on the error occurring in the N-th layer and directly propagate the error propagation value to the arbitrary layer, a weight gradient update processing unit configured to update a forward weight for the arbitrary layer based on a feed-forward value input to the arbitrary layer and the error propagation value in response to the error propagation value, and a feed-forward processing unit configured to, when update of the forward weight is completed, perform a feed-forward operation in the arbitrary layer using the forward weight. | - |
dc.title | Apparatus and method for training deep neural network using error propagation, weight gradient updating, and feed-forward processing | - |
dc.title.alternative | 오류 전파, 가중치 구배 업데이트를 사용하여 심층 신경망을 훈련시키기 위한 장치와 방법, 피드 포워드 처리 | - |
dc.type | Patent | - |
dc.type.rims | PAT | - |
dc.contributor.localauthor | Yoo, Hoi-Jun | - |
dc.contributor.assignee | KAIST | - |
dc.identifier.iprsType | 특허 | - |
dc.identifier.patentApplicationNumber | 16988737 | - |
dc.identifier.patentRegistrationNumber | 11915141 | - |
dc.date.application | 2020-08-10 | - |
dc.date.registration | 2024-02-27 | - |
dc.publisher.country | US | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.