Dropout
Dropout je stohastička tehnika regularizacije za treniranje dubokih neuronskih mreža, koju su uveli Srivastava, Hinton, Krizhevsky, Sutskever i Salakhutdinov 2014. godine. Tokom svakog koraka treniranja, svaki neuron se nezavisno isključuje sa verovatnoćom (1 − p), sprečavajući mrežu da previše čvrsto ko-adaptira svoje jedinice i time smanjujući prekomerno prilagođavanje (overfitting).
Pročitajte celu metodu
Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.
Method map
The neighbourhood of related methods — select a node to explore.
Izvori
- Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15, 1929–1958. link ↗
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 7: Regularization for Deep Learning). MIT Press. ISBN: 978-0-262-03561-3
Kako citirati ovu stranicu
ScholarGate. (2026, June 3). Dropout Regularization for Deep Neural Networks. ScholarGate. https://scholargate.app/sr/deep-learning/dropout
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Batch NormalizationDuboko učenje↔ compare
Citirana u
Uočili ste grešku na ovoj stranici? Prijavite je ili predložite ispravku →