Comparer des méthodes

	GRU auto-supervisé	Unité récurrente "gated" (GRU)
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2014–2019	2014
Auteur d'origine	Cho, K. et al. (GRU); self-supervised training paradigm from broader SSL literature	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Type	Self-supervised sequence model	Recurrent neural network with gating
Source fondatrice	Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014.	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014, pp. 1724–1734.
Alias	SS-GRU, Self-supervised Gated Recurrent Unit, GRU with self-supervised pretraining, Unsupervised GRU pretraining	GRU, GRU network, gated RNN, GRU cell
Apparentées	4	3
Résumé	Self-supervised GRU trains a Gated Recurrent Unit network using automatically constructed supervision signals — such as next-step prediction or masked token recovery — derived from the unlabeled data itself. The learned sequence representations are then fine-tuned on small labeled datasets, making high-quality sequential modeling feasible when annotations are scarce.	The Gated Recurrent Unit (GRU), introduced by Cho et al. in 2014, is a streamlined recurrent neural network that uses two learned gates — an update gate and a reset gate — to selectively retain or discard information across time steps, enabling effective sequence modelling with fewer parameters than LSTM.