Uporedite metode

	Rekurentna neuronska mreža prilagođena domenu	Доменски-адаптивни Трансформер
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2010s	2019–2022
Tvorac	Ganin et al.; Pan & Yang (domain adaptation frameworks applied to RNNs)	Various (Vaswani et al. 2017 for Transformers; domain adaptation extensions emerged 2019–2022)
Tip	Domain-adaptive sequential model	Pre-trained model fine-tuned with domain-shift adaptation
Temeljni izvor	Ganin, Y., Ustunova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1–35.	Ni, J., Hernandez Abrego, G., Constant, N., Ma, J., Hall, K., Cer, D., & Yang, Y. (2021). Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models. Findings of ACL 2022. arXiv:2108.08877.
Drugi nazivi	DA-RNN, domain-adaptive RNN, domain-adapted recurrent network, cross-domain RNN	DAT, domain-adaptive Transformer, domain adaptation with Transformers, transfer-learning Transformer
Srodne	6	2
Sažetak	A Domain-adaptive Recurrent Neural Network (DA-RNN) is a recurrent neural network trained on a source domain and adapted to a target domain using domain adaptation techniques such as adversarial training, feature alignment, or fine-tuning. It enables sequential models to generalise across domains when labeled target-domain data is scarce or unavailable.	A Domain-Adaptive Transformer (DAT) is a Transformer-based model — such as BERT or ViT — extended with an explicit domain-alignment objective so that learned representations transfer well from a labeled source domain to a different, often unlabeled, target domain. The approach combines the powerful representation capacity of Transformers with domain adaptation techniques such as adversarial training or contrastive alignment to minimise domain shift.