Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 임희철 | - |
dc.contributor.author | 김민수 | - |
dc.date.accessioned | 2023-08-01T02:10:23Z | - |
dc.date.available | 2023-08-01T02:10:23Z | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/46305 | - |
dc.description.abstract | An artificial intelligence system and a method for searching for an optimal model are provided. A method for searching for a learning mode of an artificial intelligence system includes receiving, by an operator included in a first node, first channels, deriving, by the operator included in the first node, first parameter weight indexes corresponding to weights of first parameters by calculating the first parameters corresponding to each of the received first channels with the received first channels, generating and outputting a second channel group by combining the first channel with the other channel, receiving, by an operator included in a second node, second channels included in the second channel group, and deriving, by the operator included in the second node, second parameter weight indexes corresponding to weights of second parameters by calculating the second parameters corresponding to the received second channels with the received second channels. | - |
dc.title | GPU 기반의 채널 단위 딥뉴럴 네트워크 구조 검색을 사용하는 인공지능 시스템 | - |
dc.title.alternative | GPU-BASED ARTIFICIAL INTELLIGENCE SYSTEM USING CHANNEL-LEVEL ARCHITECTURE SEARCH FOR DEEP NEURAL NETWORK | - |
dc.type | Patent | - |
dc.publisher.country | US | - |
dc.identifier.patentApplicationNumber | 16-281582 | - |
dc.date.application | 2019-02-21 | - |
dc.identifier.patentRegistrationNumber | 11,687,784 | - |
dc.date.registration | 2023-06-27 | - |
dc.contributor.assignee | (재)대구경북과학기술원(100/100) | - |
dc.type.iprs | 특허 | - |
There are no files associated with this item.