BROWSE
Detail
Journal Article
자동 기계 학습(AutoML) 기술 동향
- Issue Date
- 2019-08
- Citation
- 전자통신동향분석, v.34, no.4, pp.32-42
- ISSN
- 1225-6455
- Publisher
- 한국전자통신연구원
- Language
- Korean
- Type
- Journal Article
- Abstract
- 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.
- KSP Keywords
- Bayesian methods, Evolutionary algorithms(EAs), Future research directions, Hyperparameter optimization, Machine Learning Algorithms, Reinforcement Learning(RL), computation time, expert knowledge, neural network architecture
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
