트렌드

게시글 검색
[한국전자통신연구원] 자동 기계학습(AutoML) 기술 동향
테크포럼
2019-08-08 12:06:49

Ⅰ. 자동 기계학습(AutoML) 

Ⅱ. 하이퍼 파라미터 최적화(HPO)

Ⅲ. 신경망 아키텍처 탐색

Ⅳ. 결론 

 

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

 

 

[원문보기]

SNS 공유