השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| זיקוק ידע (Knowledge Distillation)× | מכונת וקטורים תומכים (סיווג)× | |
|---|---|---|
| תחום≠ | למידה עמוקה | למידת מכונה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2015 | 1995 |
| הוגה השיטה≠ | Hinton, G., Vinyals, O. & Dean, J. | Cortes, C. & Vapnik, V. |
| סוג≠ | Neural network compression (teacher–student) | Maximum-margin classifier (kernel method) |
| מקור מכונן≠ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗ |
| כינויים | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier |
| קשורות | 5 | 5 |
| תקציר≠ | 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. | 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. |
| ScholarGateמערך נתונים ↗ |
|
|