Sammenlign metoder

	Domene-adaptiv Multilayer Perceptron	Finjustert Multilayer Perceptron
Fagfelt	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning
Opprinnelsesår	2006–2016	1986 (MLP); fine-tuning practice formalised c. 2014
Opphavsperson	Ben-David et al.; Ganin et al.	Rumelhart, Hinton & Williams (MLP); Yosinski et al. (fine-tuning analysis)
Type	Domain adaptation of feedforward neural network	Supervised deep learning with pre-trained weight initialisation
Opprinnelig kilde	Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine Learning, 79(1–2), 151–175.	Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
Alias	DA-MLP, domain-adaptive MLP, domain-adapted feedforward network, domain adaptation with MLP	fine-tuned MLP, adapted MLP, domain-adapted multilayer perceptron, MLP fine-tuning
Relaterte	5	4
Sammendrag	A domain-adaptive multilayer perceptron (DA-MLP) is a feedforward neural network trained to learn representations that are useful across a labeled source domain and an unlabeled or differently distributed target domain. By minimizing both a task loss and a domain-discrepancy objective, the MLP generalizes to the target domain with little or no target-domain labels.	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.