Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Multi-Head Self-Attention× | XGBoost× | |
|---|---|---|
| Obor≠ | Hluboké učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2017 | 2016 |
| Tvůrce≠ | Vaswani, A. et al. | Chen, T. & Guestrin, C. |
| Typ≠ | Attention mechanism (Transformer core) | Ensemble (gradient-boosted decision trees) |
| Původní zdroj≠ | 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 ↗ |
| Další názvy≠ | 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 |
| Příbuzné | 5 | 5 |
| Shrnutí≠ | 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. |
| ScholarGateDatová sada ↗ |
|
|