Machine learningMachine learning

Učenje s malo primjera

Učenje s malo primjera (few-shot learning) je paradigma strojnog učenja koja obučava modele za prepoznavanje novih klasa ili rješavanje novih zadataka na temelju samo nekolicine označenih primjera — tipično jedan do pet — iskorištavanjem prethodnog znanja stečenog iz velike, srodne distribucije podataka za obuku. Posebno je relevantno u domenama gdje je označavanje skupo, oskudno ili strukturno ograničeno.

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.

+17 more

Izvori

  1. Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29. link
  2. Finn, C., Abbeel, P., & Levine, S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR 70:1126–1135. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Few-shot Learning (Meta-learning with Limited Labeled Examples). ScholarGate. https://scholargate.app/hr/machine-learning/few-shot-learning

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

ScholarGateFew-shot Learning (Few-shot Learning (Meta-learning with Limited Labeled Examples)). Preuzeto 2026-06-15 s https://scholargate.app/hr/machine-learning/few-shot-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026