Many forms machine learning require large amounts of data, whereas humans can often learn significantly from a single experience. This is known as single-shot learning. Symbolic machine learning such as explanation-based learning attempt 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.
Used on pages 534, 547
Also known as few-shot learning