A class is a collection of things that might reasonably be grouped together. Classes that we commonly encounter have simple names so, as humans, we can easily refer to them. The class of dogs, for example, allows me to say “my dog ate my newspaper” without having to describe a particular dog, or indeed, a particular newspaper. In machine learning, the name of the class is called the class label. Exactly what it means to belong to a class, or category, is a complex philosophical question but often we think of a class in terms of the common properties of its members. We think particularly of those properties which seperate them from other things which are in many ways similar, e.g., cats mieow and dogs bow-wow. We would be unlikely to form a class from a random collection of things, as they would share no common properties. Knowing something belonged to such a collection would be of no particular benefit....
- Buchanan, B., Barstow, D., Bechtel, R., Bennett, J., Clancey, W., Kulikowski, C., et al. (1983) Constructing an expert system. In F. Hayes-Roth, D.A. Waterman, & D.B. Lenat (Eds.), Building expert systems (pp. 127–167). Reading, MA: Addison-Wesley.Google Scholar