방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 진화 전략 (CMA-ES)× | 신경망 구조 탐색× | |
|---|---|---|
| 분야≠ | 최적화 | 딥러닝 |
| 계열≠ | Process / pipeline | Machine learning |
| 기원 연도≠ | 2001 | 2017 |
| 창시자≠ | Nikolaus Hansen & Andreas Ostermeier | Zoph, B. & Le, Q.V. |
| 유형≠ | Derivative-free continuous black-box optimizer | Automated architecture optimization (deep learning) |
| 원전≠ | Hansen, N. & Ostermeier, A. (2001). Completely Derandomized Self-Adaptation in Evolutionary Strategies. Evolutionary Computation, 9(2), 159-195. DOI ↗ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ |
| 별칭 | CMA-ES, Evolution Strategy, Evrimsel Strateji (CMA-ES), self-adapting evolution strategy | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search |
| 관련 | 5 | 5 |
| 요약≠ | CMA-ES, short for Covariance Matrix Adaptation Evolution Strategy, is a modern derivative-free optimizer for continuous black-box functions introduced by Hansen and Ostermeier in 2001. It maintains a population of candidate solutions drawn from a multivariate normal distribution and iteratively updates the distribution's mean, step size, and full covariance matrix to steer the search toward better regions of the parameter space. It has become the de-facto standard for continuous black-box optimization and is widely used in neural architecture search and reinforcement-learning policy optimization. | Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All. |
| ScholarGate데이터셋 ↗ |
|
|