Identification from Noisy Examples
With algorithms based on identification by enumeration (including refinement algorithms), an incorrect example may cause a correct hypothesis to be discarded. Even if correct hypotheses occur infinitely often in the enumeration, errors can cause them to be discarded infinitely often, and thereby frustrate convergence.
With pac-identification, the fundamental strategy of choosing a hypothesis consistent with the examples may fail, because there may be no such hypothesis.
KeywordsGood Rule Noise Rate Content Error Correct Rule Correct Hypothesis
Unable to display preview. Download preview PDF.