手法を比較

	ファインチューニングLSTM	Long Short-Term Memory (LSTM)
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2018 (fine-tuning paradigm formalised); LSTM core: 1997	1997
提唱者	Howard, J. & Ruder, S. (ULMFiT); foundational LSTM by Hochreiter & Schmidhuber	Hochreiter, S. & Schmidhuber, J.
種類	Supervised sequential model with transfer learning	Recurrent neural network with gated memory cells
原典	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.	Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
別名	Fine-Tuned LSTM, LSTM Fine-Tuning, Pre-trained LSTM with Task Adaptation, LSTM Transfer Learning	LSTM, LSTM network, LSTM-RNN, long short-term memory RNN
関連	6	4
概要	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.	Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step.