Unbiased Learner
- We could define an unbiased hypothesis space by allowing
arbitrary conjunctions, disjunctions, and negations.
- The number of possible hypothesis (ignoring semantic
repetition) is $2^{|X|}$.
- The Candidate-Elimination algorithm, if applied to
this hypothesis space, will be unable to generalize beyond the
observed examples!
- So, in order to learn the concept we would need to present
every single example.
- If we use a partially-learned concept, then exactly
half of the hypotheses will vote positive and half
negative for every unseen example.
José M. Vidal
.
29 of 31