Usporedite metode

	Višejezični perceptron višestrukih slojeva	Prilagođeni Višeslojni Perceptron
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2010s	1986 (MLP); fine-tuning practice formalised c. 2014
Tvorac	McCulloch & Pitts / Rumelhart et al. (MLP); multilingual application became standard in NLP from the 2010s onward	Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis)
Vrsta	Feedforward neural network (multilingual variant)	Supervised deep learning with pre-trained weight initialisation
Temeljni izvor	Artetxe, M., & Schwartz, H. A. (2019). Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond. Transactions of the Association for Computational Linguistics, 7, 597–610.	Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
Drugi nazivi	Multilingual MLP, cross-lingual MLP, multilingual feedforward network, multilingual FFNN	fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning
Srodne	4	4
Sažetak	A Multilingual MLP is a feedforward neural network trained on text from two or more languages, relying on shared or aligned input representations — such as multilingual word embeddings or subword vocabularies — so that a single model can process and classify text across languages without separate per-language networks.	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.