Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| Distillazione della Conoscenza× | Random Forest× | Support Vector Machine (Classificazione)× | |
|---|---|---|---|
| Campo≠ | Apprendimento profondo | Apprendimento automatico | Apprendimento automatico |
| Famiglia | Machine learning | Machine learning | Machine learning |
| Anno di origine≠ | 2015 | 2001 | 1995 |
| Ideatore≠ | Hinton, G., Vinyals, O. & Dean, J. | Breiman, L. | Cortes, C. & Vapnik, V. |
| Tipo≠ | Neural network compression (teacher–student) | Ensemble (bagging of decision trees) | Maximum-margin classifier (kernel method) |
| Fonte seminale≠ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| Alias | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| Correlati≠ | 5 | 4 | 5 |
| Sintesi≠ | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. | The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data. |
| ScholarGateInsieme di dati ↗ |
|
|
|