In machine learning the training phase uses training data to create a model that is subsequently used for new situations/imputs the application phase. In some cass there may be a separate validation phase. The two main tor training are:
- supervised learning.-- when the training data is labelled, that is each training data item consists of and input-output or input-class pair;
- unsupervised learning.-- when there is no labelling and th system looks for patterns or clusters in the data.
Defined on page 176
Used on pages 114, 163, 176