Version space learning

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^[1]

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

(i.e., one or more of hypotheses 1 through $n$ are true). 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.^[2] This iterative refining of the hypothesis space is called the candidate elimination algorithm, the hypothesis space maintained inside the algorithm, its version space.^[1]

^ ^a ^b Russell, Stuart; Norvig, Peter (2003) [1995]. Artificial Intelligence: A Modern Approach (2nd ed.). Prentice Hall. pp. 683–686. ISBN 978-0137903955.
^ Cite error: The named reference Mitchel-1982 was invoked but never defined (see the help page).

[aima-1] Russell, Stuart; Norvig, Peter (2003) [1995]. Artificial Intelligence: A Modern Approach (2nd ed.). Prentice Hall. pp. 683–686. ISBN 978-0137903955.

[Mitchel-1982-2] Cite error: The named reference Mitchel-1982 was invoked but never defined (see the help page).

[1]

[2]