Few-Shot Learning

Обзор

Few-shot learning supplies a handful of worked examples in the prompt so the model infers the task from them without any weight update. It solves the problem that fine-tuning needs labelled data, a training run and a deployment per task, while many tasks are simple enough to demonstrate in a paragraph. It exists because it emerged from scale rather than design: the capability appeared in large models that were never trained for it.

Граф технологий

Как Few-Shot Learning связана с остальным стеком.

Инструменты

ПО, которое реализует Few-Shot Learning или интегрируется с ним.

Альтернативы

• Zero-Shot concept

  Альтернатива для Few-Shot Learning · source

Сравнения

Подробные сопоставления с альтернативами выше.

• Few-Shot Learning vs Zero-Shot