Open main menu






  • (Sammut & Webb, 2011) ⇒ Claude Sammut (editor), and Geoffrey I. Webb (editor). (2011). “Discrete Attribute.” In: (Sammut & Webb, 2011)
    • QUOTE: Attributes are properties of things, ways that we, as humans, might describe them. If we were talking about the appearance of our friends, we might describe one of them as “sex female,” “hair brown,” “height 5 ft 7 in.” Linguistically, this is rather terse, but this very terseness has the advantage of limiting ambiguity. The attributes are sex, hair color, and height. For each friend, we could give the appropriate values to go along with each attribute, some examples are shown in Table 1. Attribute-value pairs are a standard way of describing things within the machine learning community. Traditionally, values have come in one of three types: binary, sex has two values; nominal, hair color has many values; real, height has an ordered set of values. Ideally, the attribute- value pairs are sufficient to describe some things accurately and to tell them apart from others. What might be described is very varied, so the attributes themselves will vary widely.


  • (Kohavi & Provost, 1998) ⇒ Ron Kohavi, and Foster Provost. (1998). “Glossary of Terms.” In: Machine Leanring 30(2-3).
    • Attribute (field, variable, feature): A quantity describing an instance. An attribute has a domain defined by the attribute type, which denotes the values that can be taken by an attribute. The following domain types are common: