Many forms machine learning require large amounts of data, whereas humans can often learn significantly from a single experience. This is known as one=shot or single-shot learning. Symbolic machine learning such as explanation-based learning attempts to mimic some of the ways in which humans achieve this. The term few-shot learning is used when algiorithms need a relatively small number of training examples, but typically more than one.
Also known as: few-shot learning
Used in glossary entries: explanation-based learning, machine learning, symbolic machine learning