Comparar métodos

	Destilação de Conhecimento	Aprendizagem por Transferência
Área	Aprendizado profundo	Aprendizado de máquina
Família	Machine learning	Machine learning
Ano de origem	2015	2010 (formalized); 1990s (early roots)
Autor original	Hinton, G., Vinyals, O. & Dean, J.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Tipo	Neural network compression (teacher–student)	Learning paradigm
Fonte seminal	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Outros nomes	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Relacionados	5	3
Resumo	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.	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.