least squares

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.

Least-squares methods work by minimising the sub of the squares of the differnce between the output of a model or system and its desired output. Examples include linear regression and backpropagation for neural networks. Similar methods can try to minimise the sum of the absolute errors, or the maximum error, but often squares are easier to work with mathematically.

Used in Chap. 7: pages 98, 104, 105; Chap. 8: page 116; Chap. 10: page 150

Also known as least squares estimate