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 pages 88, 121, 124, 171, 274, 371
Also known as unsupervised