Comparer des méthodes

	LSTM affiné	Réseau neuronal récurrent affiné
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2018 (fine-tuning paradigm formalised); LSTM core: 1997	2015–2018
Auteur d'origine	Howard, J. & Ruder, S. (ULMFiT); foundational LSTM by Hochreiter & Schmidhuber	Popularised by Howard & Ruder (ULMFiT, 2018); RNN fine-tuning concept developed iteratively in the NLP community from ~2015
Type	Supervised sequential model with transfer learning	Transfer learning / sequential model adaptation
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.	Howard, J. & Ruder, S. (2018). Universal Language Model Fine-Tuning for Text Classification. Proceedings of ACL 2018, 328–339.
Alias	Fine-Tuned LSTM, LSTM Fine-Tuning, Pre-trained LSTM with Task Adaptation, LSTM Transfer Learning	Fine-Tuned RNN, RNN Fine-Tuning, domain-adapted RNN, pre-trained RNN with downstream adaptation
Apparentées	6	6
Résumé	Fine-Tuned LSTM adapts a Long Short-Term Memory network pre-trained on a large corpus to a specific downstream task — such as text classification, sentiment analysis, or sequence labeling — by continuing training on task-specific labeled data. Popularised by the ULMFiT framework, this approach achieves strong performance even when labeled data is scarce.	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.