ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 A Design of Continuous Learning System based on Knowledge Augmentation
Cited 0 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
저자
강현중, 권순현, 김은주, 김현재, 이호성, 김귀훈, 김내수
발행일
201702
출처
International Conference on Platform Technology and Service (PlatCon) 2017, pp.1-4
DOI
https://dx.doi.org/10.1109/PlatCon.2017.7883675
초록
To create an algorithm with Machine Learning, users should understand all the knowledge such as learning rate, activation, dimension reduction, hyper parameter, neural network, etc. Therefore, in order to construct a machine learning procedure, expert knowledge is required. So, it is difficult for general users to use it. Also, experts are also hard to regenerate well-defined model if it is described only in the paper. In this paper, we propose a knowledge based Continuous Learning System (CLS) which persistently collect and infer new knowledge from information for the existing learning setup and results instantiated based on a hierarchically designed ontology model.
KSP 제안 키워드
Continuous learning, Dimension Reduction, Knowledge augmentation, Knowledge-based, Learning System, Learning procedure, Learning rate, Ontology Model, Well-defined, expert knowledge, machine Learning