In order to perform supervised traing,, we need some for =m of ground truth, that s for at least sometraining data we need to knw the correct classifiaction or output value. This may be obtained through human labelling of data, from sensor data or in some cases simulation.
Used in Chap. 8: page 115; Chap. 12: page 198; Chap. 15: page 250; Chap. 18: pages 300, 301, 308