Comparer des méthodes

	Perceptron multicouche semi-supervisé	Perceptron multicouche faiblement supervisé
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2006–2013	2016–2018
Auteur d'origine	Chapelle, O.; Scholkopf, B.; Zien, A. (eds.); Lee, D.-H.	Multiple contributors; paradigm formalized by Zhou (2018) and Ratner et al. (2016)
Type	Semi-supervised feedforward neural network	Feedforward neural network trained under weak supervision
Source fondatrice	Chapelle, O., Scholkopf, B. & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9	Zhou, Z.-H. (2018). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53.
Alias	SSL-MLP, semi-supervised MLP, semi-supervised feedforward network, partially supervised multilayer perceptron	WS-MLP, weakly supervised feedforward network, noisy-label MLP, weak-label multilayer perceptron
Apparentées	4	5
Résumé	A semi-supervised multilayer perceptron (SSL-MLP) is a feedforward neural network trained on a small pool of labeled examples together with a larger pool of unlabeled examples. By combining supervised cross-entropy loss on labeled data with an unsupervised consistency or pseudo-label objective on unlabeled data, it extracts far more signal from the data than a purely supervised MLP trained on labels alone.	A Weakly Supervised Multilayer Perceptron trains a standard feedforward neural network when only imperfect supervision is available — labels may be noisy, incomplete, crowd-sourced, rule-generated, or derived from distant supervision — enabling learning at scale without the cost of full expert annotation.