Comparer des méthodes

	Réseau neuronal récurrent affiné	Transformer affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2015–2018	2017–2019
Auteur d'origine	Popularised by Howard & Ruder (ULMFiT, 2018); RNN fine-tuning concept developed iteratively in the NLP community from ~2015	Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
Type	Transfer learning / sequential model adaptation	Transfer learning / supervised fine-tuning
Source fondatrice	Howard, J. & Ruder, S. (2018). Universal Language Model Fine-Tuning for Text Classification. Proceedings of ACL 2018, 328–339.	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Alias	Fine-Tuned RNN, RNN Fine-Tuning, domain-adapted RNN, pre-trained RNN with downstream adaptation	Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer
Apparentées	6	4
Résumé	A Fine-Tuned Recurrent Neural Network (RNN) starts from a model pre-trained on large corpora or time-series data and adapts its weights to a specific downstream task through controlled gradient updates. The approach dramatically cuts the labeled data needed for strong sequence modeling performance in text classification, named entity recognition, sentiment analysis, and related tasks.	Fine-tuning a Transformer adapts a large pre-trained model — such as BERT, GPT, or ViT — to a specific downstream task by continuing gradient-based training on a labelled target dataset. This two-stage paradigm (pre-train then fine-tune) consistently achieves state-of-the-art results across NLP and computer vision tasks with far less task-specific data than training from scratch.