single-shot learning

Terms from Artificial Intelligence: humans at the heart of algorithms

Page numbers are for draft copy at present; they will be replaced with correct numbers when final book is formatted. Chapter numbers are correct and will not change now.

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 in Chap. 22: pages 365, 374

Also known as few-shot learning