방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 신경망 구조 탐색× | 확률적 최적화× | |
|---|---|---|
| 분야≠ | 딥러닝 | 최적화 |
| 계열≠ | Machine learning | Process / pipeline |
| 기원 연도≠ | 2017 | 1951 (SGD); 2014 (Adam) |
| 창시자≠ | Zoph, B. & Le, Q.V. | — |
| 유형≠ | Automated architecture optimization (deep learning) | Gradient-based iterative optimization |
| 원전≠ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ | Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. Annals of Mathematical Statistics, 22(3), 400-407. DOI ↗ |
| 별칭≠ | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search | Stokastik Optimizasyon (SGD & Varyantları), stochastic gradient descent, SGD, Adam |
| 관련≠ | 5 | 3 |
| 요약≠ | 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. | Stochastic optimization is a family of iterative methods that minimize an objective function by computing gradients on randomly sampled subsets of data — mini-batches — rather than on the entire dataset at once. Pioneered by Robbins and Monro in 1951 as stochastic approximation, the approach became the standard engine for training large-scale machine-learning models through variants such as SGD with momentum, AdaGrad, RMSProp, and Adam. |
| ScholarGate데이터셋 ↗ |
|
|