השוואת שיטות

	Transfer Learning	למידה בפיקוח עצמי	למידה מונחית-למחצה
תחום	למידת מכונה	למידת מכונה	למידת מכונה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2010 (formalized); 1990s (early roots)	2018–2020	1970s–2006 (formalized)
הוגה השיטה	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)	LeCun, Y. and community (formalized ~2018–2020)	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
סוג	Learning paradigm	Representation learning paradigm	Learning paradigm
מקור מכונן	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
כינויים	TL, domain adaptation, fine-tuning, pre-trained model adaptation	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
קשורות	3	3	5
תקציר	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.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.