DC Field | Value | Language |
---|---|---|
dc.contributor.author | 황성주 | ko |
dc.contributor.author | 한문수 | ko |
dc.contributor.author | 강민기 | ko |
dc.contributor.author | 정현우 | ko |
dc.date.accessioned | 2024-05-14T10:00:52Z | - |
dc.date.available | 2024-05-14T10:00:52Z | - |
dc.identifier.uri | http://hdl.handle.net/10203/319367 | - |
dc.description.abstract | Provided is a memory-based reinforcement learning method and system capable of storing optional information in streaming data. A question-answering (QA) method using memory-based reinforcement learning method includes receiving, in an episodic memory reader (EMR), streaming data about an input context that is input from a user; analyzing, in the EMR, the received streaming data and storing preset semantic information used for QA in an external memory; and, in response to an input of a question front the user, determining, in a pretrained QA model, an answer to the input question based on semantic information stored in the external memory. | - |
dc.title | Memory-based reinforcement learning method for storing optional information in streaming data and system therefore | - |
dc.title.alternative | 스트리밍 데이터에서 선택적 정보 저장이 가능한 메모리 기반 강화 학습 방법 및 그 시스템 | - |
dc.type | Patent | - |
dc.type.rims | PAT | - |
dc.contributor.localauthor | 황성주 | - |
dc.contributor.assignee | KAIST | - |
dc.identifier.iprsType | 특허 | - |
dc.identifier.patentApplicationNumber | 17179178 | - |
dc.identifier.patentRegistrationNumber | 11875119 | - |
dc.date.application | 2021-02-18 | - |
dc.date.registration | 2024-01-16 | - |
dc.publisher.country | US | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.