Also known as: Few shot Learning Β· Few Shot Learning
Few-shot learning is the ability of a model to learn or adapt to a new task from only a small number of examples. It is important when labeled data is scarce and is often associated with transfer learning, meta-learning, and large language model prompting.
A machine learning approach, often used for object classification, designed to train effective classification models from only a small number of training examples. See also one-shot learning and zero-shot learning.