Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| Ricerca Architetturale Neurale× | XGBoost× | |
|---|---|---|
| Campo≠ | Apprendimento profondo | Apprendimento automatico |
| Famiglia | Machine learning | Machine learning |
| Anno di origine≠ | 2017 | 2016 |
| Ideatore≠ | Zoph, B. & Le, Q.V. | Chen, T. & Guestrin, C. |
| Tipo≠ | Automated architecture optimization (deep learning) | Ensemble (gradient-boosted decision trees) |
| Fonte seminale≠ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗ |
| Alias≠ | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search | XGBoost, extreme gradient boosting, scalable tree boosting |
| Correlati | 5 | 5 |
| Sintesi≠ | 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. | 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. |
| ScholarGateInsieme di dati ↗ |
|
|