Concept
Few-shot
Few-shot learning means giving a model a handful of task examples at inference time, then asking it to handle a new case, with no weight updates. Contrast it with fine-tuning: instead of running gradient descent on a labeled dataset to specialize the model, you paste the…
The rest of “Few-shot” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→