Σύγκριση μεθόδων

	Διαδικτυακή Μάθηση Ελάχιστων Δεδομένων (Online Few-shot Learning)	Εκμάθηση μεταφοράς
Πεδίο	Μηχανική Μάθηση	Μηχανική Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2019	2010 (formalized); 1990s (early roots)
Δημιουργός	Finn, C. et al. (online meta-learning formalization)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Τύπος	Online learning + meta-learning hybrid	Learning paradigm
Θεμελιώδης πηγή	Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Εναλλακτικές ονομασίες	online meta-learning, streaming few-shot learning, continual few-shot learning, incremental few-shot learning	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Συναφείς	4	3
Σύνοψη	Online Few-shot Learning combines the streaming update principle of online learning with the data-efficiency goal of few-shot learning, enabling a model to continuously adapt to new tasks or classes from only a handful of labeled examples as data arrives sequentially — without access to the full historical dataset.	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.