Salīdzināt metodes

	Pašuzraudzītā pārneses apmācība	Pašuzraudzības apmācība
Nozare	Mašīnmācīšanās	Mašīnmācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2018–2020 (modern consolidation)	2018–2020
Autors	LeCun, Y. (concept); Devlin et al. (BERT, NLP); Chen et al. (SimCLR, vision)	LeCun, Y. and community (formalized ~2018–2020)
Tips	Learning paradigm (self-supervised pre-training + fine-tuning)	Representation learning paradigm
Pirmavots	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607.	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/
Citi nosaukumi	self-supervised pre-training, SSL-based transfer learning, representation transfer from self-supervised models, contrastive pre-training with transfer	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Saistītās	6	3
Kopsavilkums	Self-supervised transfer learning combines two powerful paradigms: a model first learns rich representations from unlabeled data using self-supervised pretext tasks, then those learned representations are transferred and fine-tuned on a downstream task with limited labeled data. This approach underlies landmark systems such as BERT in NLP and SimCLR and DINO in computer vision, dramatically reducing labeled-data requirements across many domains.	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.