Usporedite metode

	Prilagođeni Višeslojni Perceptron	Prilagođeni LSTM
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	1986 (MLP); fine-tuning practice formalised c. 2014	2018 (fine-tuning paradigm formalised); LSTM core: 1997
Tvorac	Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis)	Howard, J. & Ruder, S. (ULMFiT); foundational LSTM by Hochreiter & Schmidhuber
Vrsta	Supervised deep learning with pre-trained weight initialisation	Supervised sequential model with transfer learning
Temeljni izvor	Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	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.
Drugi nazivi	fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning	Fine-Tuned LSTM, LSTM Fine-Tuning, Pre-trained LSTM with Task Adaptation, LSTM Transfer Learning
Srodne	4	6
Sažetak	A Fine-Tuned Multilayer Perceptron starts from weights learned on a source task — or a large general-purpose dataset — and continues training on a smaller target dataset with a reduced learning rate. This reuse of pre-learned representations allows the MLP to converge faster and generalise better than training from scratch, especially when labelled target data is scarce.	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.