Batch Normalization
Batch Normalization je tehnika obučavanja koju su uveli Sergej Ioffe i Kristijan Sizedi 2015. godine, a koja normalizuje pre-aktivacione izlaze svakog sloja koristeći srednju vrednost i varijansu izračunate na trenutnom mini-baču. Stabilizacijom distribucije ulaza u svaki sloj tokom obučavanja, značajno se smanjuje unutrašnji kovarijantni pomeraj, omogućavajući korišćenje viših stopa učenja i čineći duboke mreže bržim i pouzdanijim za obučavanje.
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
- Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), PMLR 37, 448–456. link ↗
- Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning (Ch. 8). MIT Press. ISBN: 978-0-262-03561-3
- Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167. link ↗
Kako citirati ovu stranicu
ScholarGate. (2026, June 3). Batch Normalization (Normalizing Layer Activations per Mini-Batch). ScholarGate. https://scholargate.app/sr/deep-learning/batch-normalization
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.
Compare side by side →Citirana u
Uočili ste grešku na ovoj stranici? Prijavite je ili predložite ispravku →