방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 신경망 구조 탐색× | 전문가 혼합× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도 | 2017 | 2017 |
| 창시자≠ | Zoph, B. & Le, Q.V. | Shazeer, N. et al. |
| 유형≠ | Automated architecture optimization (deep learning) | Sparse neural network architecture (conditional computation) |
| 원전≠ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ |
| 별칭≠ | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search | Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts |
| 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. | Mixture of Experts (MoE) is a sparse neural-network architecture, introduced by Shazeer and colleagues in 2017 with the sparsely-gated MoE layer, in which only a subset of expert sub-networks is activated for each input. As seen in models such as Switch Transformer and Mixtral, it holds computation cost fixed even as the total parameter count grows. |
| ScholarGate데이터셋 ↗ |
|
|