A concept 
over a domain 
, in machine learning theory and
artificial intelligence, is a 
-valued
function 
. A collection of
concepts is called a concept class.
In context-specific applications, concepts are usually thought to assign either a "positive" or "negative" outcome (corresponding to range
values of 1 or 0, respectively) to each element 
of the domain 
. In that way, concepts are the fundamental component
of learning theory.
