Few-Shot Learning
Few-shot learning is a machine learning approach where a model learns to perform a new task from only a handful of training examples — sometimes as few as one to five. Unlike traditional machine learning that requires thousands of labeled examples, few-shot learning leverages prior knowledge from pre-training to generalize from minimal data. It is a broader concept than few-shot prompting, encompassing both in-context examples and training-time techniques for learning from scarce data.
Example
A medical imaging system needs to identify a rare skin condition with only 5 labeled photos in its database. Using few-shot learning, the model draws on patterns it learned from millions of other medical images during pre-training and identifies the condition accurately — rather than requiring the thousands of examples that traditional training would need.
Related Terms
Put this into practice
Build polished, copy-ready prompts in under 60 seconds with SurePrompts.
Try SurePrompts