Nominal variable

The level of measurement of a variable in mathematics and statistics is a classification that was proposed in order to describe the nature of information contained within numbers assigned to objects and, therefore, within the variable. The levels were proposed by Stanley Smith Stevens in his 1946 article On the theory of scales of measurement. According to Stevens' theory of scales, different mathematical operations on variables are possible, depending on the level at which a variable is measured.
See more at Wikipedia.org...

Variables which take on one of a set of discrete values, such as Gender={Male, Female}. In neural networks, nominal output variables are used to distinguish classification tasks from regression tasks. See also, Grouping (or Coding) Variable and Measurement scales.