Usporedite metode

	T5 (Text-to-Text Transfer Transformer)	Attention Mechanism	Prijenosno učenje
Područje	Duboko učenje	Duboko učenje	Strojno učenje
Obitelj	Machine learning	Machine learning	Machine learning
Godina nastanka	2020	2015	2010 (formalized); 1990s (early roots)
Tvorac	Raffel, C.; Shazeer, N.; Roberts, A.; et al. (Google Brain)	Bahdanau, D.; Luong, M.T.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Vrsta	Pre-trained encoder-decoder Transformer (sequence-to-sequence)	Neural attention layer (encoder-decoder)	Learning paradigm
Temeljni izvor	Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, 21(140), 1–67.	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Drugi nazivi	T5, Text-to-Text Transfer Transformer, T5-Small, T5-Base	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Srodne	2	5	3
Sažetak	T5 is a unified sequence-to-sequence deep learning framework introduced by Raffel et al. at Google Brain in 2020, published in the Journal of Machine Learning Research (Vol. 21, No. 140). It reframes every NLP task — classification, translation, summarisation, question answering, and more — as a text-to-text problem: both input and output are always character strings, enabling a single encoder-decoder Transformer to be pre-trained once and fine-tuned across tasks with a consistent interface. T5 introduced span-corruption pre-training and the C4 corpus, and its largest variant (11B parameters) achieved state-of-the-art results across a wide range of NLP benchmarks at the time of publication.	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.