ScholarGate
دستیار

مقایسهٔ روش‌ها

روش‌های انتخابی خود را کنار هم مرور کنید؛ ردیف‌های متفاوت برجسته شده‌اند.

تقطیر دانش (Knowledge Distillation)×یادگیری انتقالی×
حوزهیادگیری عمیقیادگیری ماشین
خانوادهMachine learningMachine learning
سال پیدایش20152010 (formalized); 1990s (early roots)
پدیدآورHinton, G., Vinyals, O. & Dean, J.Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
نوعNeural network compression (teacher–student)Learning paradigm
منبع بنیادینHinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗
نام‌های دیگرBilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationTL, domain adaptation, fine-tuning, pre-trained model adaptation
مرتبط53
خلاصهKnowledge 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.Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.
ScholarGateمجموعه‌داده
  1. v1
  2. 2 منابع
  3. PUBLISHED
  1. v1
  2. 2 منابع
  3. PUBLISHED

رفتن به جست‌وجو دریافت اسلایدها

ScholarGateمقایسهٔ روش‌ها: Knowledge Distillation · Transfer Learning. بازیابی‌شده در 2026-06-16 از https://scholargate.app/fa/compare