Sammenlign metoder

	Selv-supervisert støttevektormaskin	Selv-supervisert læring
Fagfelt	Maskinlæring	Maskinlæring
Familie	Machine learning	Machine learning
Opprinnelsesår	2019–2021	2018–2020
Opphavsperson	Various (integration of self-supervised learning with SVM classifiers, ~2019–2021)	LeCun, Y. and community (formalized ~2018–2020)
Type	Hybrid (self-supervised pretraining + SVM classifier)	Representation learning paradigm
Opprinnelig kilde	De Palma, A., Bucarelli, M. S., Goyal, P., & Silvestri, F. (2021). Self-supervised Support Vector Machine. Proceedings of the AAAI Workshop on Self-Supervised Learning for the Internet of Things.	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/
Alias	Self-supervised SVM, SS-SVM, semi-self-supervised SVM, self-supervised kernel SVM	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Relaterte	5	3
Sammendrag	A Self-supervised Support Vector Machine combines self-supervised pretraining — learning representations from unlabeled data via pretext tasks — with a Support Vector Machine classifier trained on the resulting features. This hybrid approach enables strong classification performance even when labeled data is scarce, by leveraging the structure embedded in large unlabeled datasets before applying the SVM's margin-maximization objective.	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.