Version space learning is a logical approach to machine learning, specifically binary classification. Version space learning algorithms search a predefined space of hypotheses, viewed as a set of logical sentences. Formally, the hypothesis space is a disjunction

${\displaystyle H_{1}\lor H_{2}\lor ...\lor H_{n}}$

(i.e., either hypothesis 1 is true, or hypothesis 2, or any subset of the hypotheses 1 through n). A version space learning algorithm is presented with examples, which it will use to restrict its hypothesis space; for each example x, the hypotheses that are inconsistent with x are removed from the space. This iterative refining of the hypothesis space is called the candidate elimination algorithm, the hypothesis space maintained inside the algorithm its version space.