동향

[전자통신동향분석]자동 기계학습(AutoML) 기술 동향

분야

정보/통신

발행기관

한국전자통신연구원

발행일

2019.08.01

URL


초록
The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.


 

리포트 평점  
해당 콘텐츠에 대한 회원님의 소중한 평가를 부탁드립니다.
0.0 (0개의 평가)
평가하기
등록된 댓글이 없습니다.