unsupervised 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.

In unsupervised learning the training set is unlabelled, that is it has no markers to indicate a desired grouping or value. Unsupervised learning algorithms look for commonalities to group or infer other properties of the data. This may be used on its own, or be used as the first stage before human labelling or for a subsequent supervised learning method.

Defined on page 88

Used on Chap. 5: page 88; Chap. 6: pages 121, 124; Chap. 8: pages 154, 160, 162, 170; Chap. 9: pages 176, 177, 178, 188, 189, 194, 195, 196; Chap. 10: page 211; Chap. 12: page 278; Chap. 14: page 330; Chap. 16: page 377; Chap. 18: pages 439, 440, 446

Also known as unsupervised, unsupervised algorithm, unsupervised algorithms, unsupervised approach, unsupervised machine learning, unsupervised technique, unsupervised training