ScholarGate
Assistent
Machine learningMachine learning

Online Few-shot Learning

Online Few-shot Learning kombinerer princippet om streaming-opdatering fra online læring med datadrevet effektivitet fra few-shot learning, hvilket muliggør, at en model kontinuerligt kan tilpasse sig nye opgaver eller klasser ud fra kun en håndfuld mærkede eksempler, efterhånden som data ankommer sekventielt — uden adgang til hele det historiske datasæt.

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.

Kilder

  1. Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930. link
  2. Javed, K., & White, M. (2019). Meta-Learning Representations for Continual Learning. Advances in Neural Information Processing Systems (NeurIPS), 32. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Online Few-shot Learning (Streaming Meta-Learning from Scarce Labels). ScholarGate. https://scholargate.app/da/machine-learning/online-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
ScholarGateOnline Few-shot Learning (Online Few-shot Learning (Streaming Meta-Learning from Scarce Labels)). Hentet 2026-06-15 fra https://scholargate.app/da/machine-learning/online-few-shot-learning · Datasæt: https://doi.org/10.5281/zenodo.20539026