Machine learning

VGGNet (veoma duboke konvolucione mreže)

VGGNet je arhitektura duboke konvolucione neuronske mreže koju su predstavili Karen Simonyan i Andrew Zisserman iz Visual Geometry Group, Oxford, 2014. godine (objavljena na ICLR 2015). Pokazala je da je dubina mreže — postignuta isključivo slaganjem malih 3x3 konvolucionih filtera — najkritičniji faktor za visoku tačnost klasifikacije slika, a njene dve kanonske varijante (VGG-16 i VGG-19) postale su dominantne referentne arhitekture za dizajn CNN-a tokom sredine 2010-ih.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV]. Published at ICLR 2015. DOI: 10.48550/arXiv.1409.1556
  2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9: Convolutional Networks). MIT Press. ISBN: 978-0-262-03561-3

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Very Deep Convolutional Networks for Large-Scale Image Recognition (VGGNet). ScholarGate. https://scholargate.app/sr/deep-learning/vggnet

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

ScholarGateVGGNet (Very Deep Convolutional Networks for Large-Scale Image Recognition (VGGNet)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/vggnet · Skup podataka: https://doi.org/10.5281/zenodo.20539026