Machine learning

AlexNet

AlexNet je duboka konvoluciona neuronska mreža (CNN) koju su predstavili Alex Krizhevsky, Ilya Sutskever i Geoffrey Hinton 2012. godine. Pobedila je na takmičenju ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2012) sa stopom greške od 15,3% u top-5 kategoriji, nadmašivši drugoplasiranog za više od 10 procentnih poena i ponovo probudivši široko interesovanje za duboko učenje. Arhitektura je uvela ili popularizovala nekoliko tehnika — ReLU aktivacije, dropout regularizaciju i obuku na više GPU-a — koje su postale standardna praksa u celoj oblasti.

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. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25, 1097–1105. (Republished: Communications of the ACM, 60(6), 84–90, 2017.) DOI: 10.1145/3065386
  2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9: Convolutional Networks). MIT Press. ISBN: 978-0-262-03561-3
  3. LeCun, Y., Bengio, Y., & Hinton, G. E. (2015). Deep Learning. Nature, 521, 436–444. DOI: 10.1038/nature14539

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). AlexNet (Krizhevsky–Sutskever–Hinton Deep Convolutional Neural Network). ScholarGate. https://scholargate.app/sr/deep-learning/alexnet

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

ScholarGateAlexNet (AlexNet (Krizhevsky–Sutskever–Hinton Deep Convolutional Neural Network)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/alexnet · Skup podataka: https://doi.org/10.5281/zenodo.20539026