Compara mètodes

	Votació d'conjunt semisupervisada	Aprenentatge autosupervisat
Camp	Aprenentatge automàtic	Aprenentatge automàtic
Família	Machine learning	Machine learning
Any d'origen	1998–2005	2018–2020
Autor original	Zhou, Z.-H. & Li, M. (tri-training); Blum & Mitchell (co-training)	LeCun, Y. and community (formalized ~2018–2020)
Tipus	Semi-supervised ensemble (voting)	Representation learning paradigm
Font seminal	Zhou, Z.-H., & Li, M. (2005). Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering, 17(11), 1529–1541.	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/
Àlies	semi-supervised majority vote, SSL voting ensemble, co-training voting classifier, semi-supervised multi-classifier voting	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Relacionats	5	3
Resum	A semi-supervised voting ensemble trains multiple classifiers on a small labeled set, then iteratively exploits unlabeled data by having the classifiers label examples they agree on, expanding the training pool until all classifiers vote jointly on test examples. It combines the label-efficiency of semi-supervised learning with the variance-reduction of majority-vote ensembles, making it valuable when annotation is costly.	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.