ScholarGate
עוזר

השוואת שיטות

סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.

זיקוק ידע (Knowledge Distillation)×מכונת וקטורים תומכים (סיווג)×
תחוםלמידה עמוקהלמידת מכונה
משפחהMachine learningMachine learning
שנת המקור20151995
הוגה השיטהHinton, G., Vinyals, O. & Dean, J.Cortes, C. & Vapnik, V.
סוגNeural network compression (teacher–student)Maximum-margin classifier (kernel method)
מקור מכונןHinton, 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 ↗
כינוייםBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
קשורות55
תקצירKnowledge 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
  1. v1
  2. 2 מקורות
  3. PUBLISHED
  1. v1
  2. 1 מקורות
  3. PUBLISHED

מעבר לחיפוש הורדת מצגת

ScholarGateהשוואת שיטות: Knowledge Distillation · Support Vector Machine. אוחזר בתאריך 2026-06-19 מתוך https://scholargate.app/he/compare