Concept learning is when the coal of learing is to allocate input into one of a number of distinct classifications. Often concept learing is applied to. binary condition 'in category' vs 'not in category', and some algorithms or typically expressed in this binary form. Examples of concept learning include symbolic algirthms such as version spaces and ID3, and also sub-symbolic technqies including many kinds of neural network and swarm computing.
Defined on page 93
Used on Chap. 3: page 46; Chap. 5: pages 91, 93, 94; Chap. 16: pages 375, 387; Chap. 18: page 439