ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Transferlæring med konvolutionelle neurale netværk

Transferlæring med CNN genbruger et konvolutionelt neuralt netværk, der allerede er trænet på et stort datasæt – oftest ImageNet – og tilpasser dets indlærte feature-detektorer til et nyt, ofte mindre måldatasæt. Dette gør det muligt for forskere at opnå stærk billedgenkendelsespræstation uden de massive beregnings- og dataressourcer, der kræves for at træne et CNN fra bunden.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

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

+4 more

Kilder

  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

Sådan citerer du denne side

ScholarGate. (2026, June 3). Transfer Learning with Convolutional Neural Network (Feature Extraction and Fine-Tuning). ScholarGate. https://scholargate.app/da/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

Refereret af

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