rote learning

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

In rote learning one learns precisely the examples given. For humans this can be hard, but for a machine it is easy, just store all training examples with ther exepcted output and then lookup the correct value. On its own this cannot generalize, when faced with a novel input that it has not seen before it has no way of filling in or estimating the correct output based on the inputs. While this is a very simple form of machine learning, it can be a valuable part of more complex learning systems.

Used in Chap. 3: page 31; Chap. 5: page 61; Chap. 15: page 222

Also known as memorizing