Machine learningDeep learning / NLP / CV

Preneseno učenje s konvolucijskim neuronskim mrežama

Preneseno učenje s pomoću CNN-a (konvolucijske neuronske mreže) ponovno koristi konvolucijsku neuronsku mrežu koja je već obučena na velikom skupu podataka — najčešće ImageNet — te prilagođava njezine naučene detektore značajki novom, često manjem ciljnom skupu podataka. To istraživačima omogućuje postizanje snažnih performansi u prepoznavanju slika bez ogromnih računalnih resursa i podataka potrebnih za obuku CNN-a od nule.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

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

+4 more

Izvori

  1. Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI: 10.1109/TKDE.2009.191
  2. Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Transfer Learning with Convolutional Neural Network (Feature Extraction and Fine-Tuning). ScholarGate. https://scholargate.app/hr/deep-learning/transfer-learning-with-convolutional-neural-network

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

ScholarGateTransfer Learning with Convolutional Neural Network (Transfer Learning with Convolutional Neural Network (Feature Extraction and Fine-Tuning)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/transfer-learning-with-convolutional-neural-network · Skup podataka: https://doi.org/10.5281/zenodo.20539026