Machine learningDeep learning / NLP / CV

Fino podešeni Transformer

Fino podešavanje Transformera prilagođava veliki, prethodno trenirani model — kao što su BERT, GPT ili ViT — specifičnom zadatku nastavljajući obuku zasnovanu na gradijentu na obeleženom ciljnom skupu podataka. Ova dvostepena paradigma (prethodno treniranje, zatim fino podešavanje) dosledno postiže najsavremenije rezultate u zadacima obrade prirodnog jezika (NLP) i kompjuterskog vida sa daleko manje podataka specifičnih za zadatak nego obuka od nule.

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.

+4 more

Izvori

  1. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. link
  2. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Fine-Tuned Transformer (Task-Specific Adaptation of Pre-Trained Transformer Models). ScholarGate. https://scholargate.app/sr/deep-learning/fine-tuned-transformer

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

ScholarGateFine-Tuned Transformer (Fine-Tuned Transformer (Task-Specific Adaptation of Pre-Trained Transformer Models)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/fine-tuned-transformer · Skup podataka: https://doi.org/10.5281/zenodo.20539026