Porovnat metody

	Vícevrstvý perceptron adaptivní na doménu	Vícevrstvý perceptron (MLP)
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2006–2016	1986
Tvůrce	Ben-David et al.; Ganin et al.	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
Typ	Domain adaptation of feedforward neural network	Supervised feedforward neural network
Původní zdroj	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.
Další názvy	DA-MLP, domain-adaptive MLP, domain-adapted feedforward network, domain adaptation with MLP	MLP, feedforward neural network, fully connected neural network, vanilla neural network
Příbuzné	5	4
Shrnutí	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 Multilayer Perceptron is a classic fully connected feedforward neural network trained with the backpropagation algorithm, as formalised by Rumelhart, Hinton & Williams in their landmark 1986 Nature paper. Composed of an input layer, one or more hidden layers of neurons, and an output layer, the MLP learns nonlinear mappings from input features to target outputs and serves as the foundational building block of modern deep learning.