방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 다중 헤드 셀프 어텐션× | XGBoost× | |
|---|---|---|
| 분야≠ | 딥러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2017 | 2016 |
| 창시자≠ | Vaswani, A. et al. | Chen, T. & Guestrin, C. |
| 유형≠ | Attention mechanism (Transformer core) | Ensemble (gradient-boosted decision trees) |
| 원전≠ | Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗ |
| 별칭≠ | Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention | XGBoost, extreme gradient boosting, scalable tree boosting |
| 관련 | 5 | 5 |
| 요약≠ | Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5. | XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions. |
| ScholarGate데이터셋 ↗ |
|
|