Comparer des méthodes

	Apprentissage par transfert avec LSTM	Unité récurrente "gated" (GRU)
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2018 (ULMFiT; concept since ~2010)	2014
Auteur d'origine	Howard, J. & Ruder, S. (ULMFiT); general concept: Pan & Yang (2010)	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Type	Transfer learning / Sequential model	Recurrent neural network with gating
Source fondatrice	Howard, J. & Ruder, S. (2018). Universal Language Model Fine-Tuning for Text Classification. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 328–339.	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	LSTM Transfer Learning, Pre-trained LSTM, LSTM Fine-Tuning, ULMFiT-style LSTM Transfer	GRU, GRU network, gated RNN, GRU cell
Apparentées	5	3
Résumé	Transfer Learning with LSTM is a technique in which a Long Short-Term Memory network is first pre-trained on a large source corpus or task, and then its learned weights are transferred and fine-tuned on a smaller target task. This approach, popularized by ULMFiT (Howard & Ruder, 2018), allows LSTM-based models to reach strong performance even when labeled target data is 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.